-
Date submitted2023-10-29
-
Date accepted2024-04-08
-
Date published2025-02-25
Evaluation of the impact of the distance determination function on the results of optimization of the geographical placement of renewable energy sources-based generation using a metaheuristic algorithm
- Authors:
- Andrei M. Bramm
- Stanislav A. Eroshenko
Since the United Power System was created electrical supply of remote and hard-to-reach areas remains one of the topical issues for the power industry of Russia. Nowadays, usage of various renewable energy sources to supply electricity at remote areas has become feasible alternative to usage of diesel-based generation. It becomes more suitable with world decarbonization trends, the doctrine of energy security of Russia directives, and equipment cost decreasing for renewable energy sources-based power plants construction. Geological exploration is usually conducted at remote territories, where the centralized electrical supply can not be realized. Placement of large capacity renewable energy sources-based generation at the areas of geological expeditions looks perspective due to development of industrial clusters and residential consumers of electrical energy at those territories later on. Various metaheuristic methods are used to solve the task of optimal renewable energy sources-based generation geographical placement. The efficiency of metaheuristics depends on proper tuning of that methods hyperparameters, and high quality of big amount of meteorological and climatic data. The research of the effects of the calculation methods defining distance between agents of the algorithm on the optimization of renewable generation placement results is presented in this article. Two methods were studied: Euclidean distance and haversine distance. There were two cases considered to evaluate the effects of distance calculation method change. The first one was for a photovoltaic power plant with installed capacity of 45 MW placement at the Vagaiskii district of the Tyumen region. The second one was for a wind power plant with installed capacity of 25 MW at the Tungokochenskii district of the Trans-Baikal territory. The obtained results show low effects of distance calculation method change at average but the importance of its proper choose in case of wind power optimal placement, especially for local optima’s identification.
-
Date submitted2023-11-10
-
Date accepted2024-06-03
-
Date published2025-02-25
Enhancing the interpretability of electricity consumption forecasting models for mining enterprises using SHapley Additive exPlanations
- Authors:
- Pavel V. Matrenin
- Alina I. Stepanova
The objective of this study is to enhance user trust in electricity consumption forecasting systems for mining enterprises by applying explainable artificial intelligence methods that provide not only forecasts but also their justifications. The research object comprises a complex of mines and ore processing plants of a company purchasing electricity on the wholesale electricity and power market. Hourly electricity consumption data for two years, schedules of planned repairs and equipment shutdowns, and meteorological data were utilized. Ensemble decision trees were applied for time series forecasting, and an analysis of the impact of various factors on forecasting accuracy was conducted. An algorithm for interpreting forecast results using the SHapley Additive exPlanation method was proposed. The mean absolute percentage error was 7.84 % with consideration of meteorological factors, 7.41 % with consideration of meteorological factors and a load plan formulated by an expert, and the expert's forecast error was 9.85 %. The results indicate that the increased accuracy of electricity consumption forecasting, considering additional factors, further improves when combining machine learning methods with expert evaluation. The development of such a system is only feasible using explainable artificial intelligence models.
-
Date submitted2021-05-13
-
Date accepted2022-11-28
-
Date published2022-12-29
Reproduction of reservoir pressure by machine learning methods and study of its influence on the cracks formation process in hydraulic fracturing
Hydraulic fracturing is an effective way to stimulate oil production, which is currently widely used in various conditions, including complex carbonate reservoirs. In the conditions of the considered field, hydraulic fracturing leads to a significant differentiation of technological efficiency indicators, which makes it expedient to study in detail the crack formation patterns. For all affected wells, the assessment of the resulting fractures spatial orientation was performed using the developed indirect technique, the reliability of which was confirmed by geophysical methods. In the course of the analysis, it was found that in all cases the fracture is oriented in the direction of the development system element area, which is characterized by the maximum reservoir pressure. At the same time, reservoir pressure values for all wells were determined at one point in time (at the beginning of hydraulic fracturing) using machine learning methods. The reliability of the used machine learning methods is confirmed by high convergence with the actual (historical) reservoir pressures obtained during hydrodynamic studies of wells. The obtained conclusion about the influence of the formation pressure on the patterns of fracturing should be taken into account when planning hydraulic fracturing in the considered conditions.
-
Date submitted2022-05-13
-
Date accepted2022-09-24
-
Date published2022-11-03
Rapid detection of coal ash based on machine learning and X-ray fluorescence
Real-time testing of coal ash plays a vital role in the chemical, power generation, metallurgical, and coal separation sectors. The rapid online testing of coal ash using radiation measurement as the mainstream technology has problems such as strict coal sample requirements, poor radiation safety, low accuracy, and complicated equipment replacement. In this study, an intelligent detection technique based on feed-forward neural networks and improved particle swarm optimization (IPSO-FNN) is proposed to predict coal quality ash content in a fast, accurate, safe，and convenient manner. The data set was obtained by testing the elemental content of 198 coal samples with X-ray fluorescence (XRF). The types of input elements for machine learning (Si, Al, Fe, K, Ca, Mg, Ti, Zn, Na, P) were determined by combining the X-ray photoelectron spectroscopy (XPS) data with the change in the physical phase of each element in the coal samples during combustion. The mean squared error and coefficient of determination were chosen as the performance measures for the model. The results show that the IPSO algorithm is useful in adjusting the optimal number of nodes in the hidden layer. The IPSO-FNN model has strong prediction ability and good accuracy in coal ash prediction. The effect of the input element content of the IPSO-FNN model on the ash content was investigated, and it was found that the potassium content was the most significant factor affecting the ash content. This study is essential for real-time online, accurate, and fast prediction of coal ash.