Search

Medium-term forecasting of water inflow is of great importance for small hydroelectric power plants operating in remote power supply areas and having a small reservoir. Improving the forecasting accuracy is aimed at solving the problem of determining the water reserve for the future generation of electricity at hydroelectric power plants, taking into account the regulation in the medium term. Medium-term regulation is necessary to amplify the load in the peak and semi-peak portions of the load curve. The solution to such problems is aggravated by the lack of sufficiently reliable information on water inflow and prospective power consumption, which is of a stochastic nature. In addition, the mid-term planning of electricity generation should consider the seasonality of changes in water inflow, which directly affects the reserves and the possibility of regulation. The paper considers the problem of constructing a model for medium-term forecasting of water inflow for planning electricity generation, taking into account climatic changes in isolated power systems. Taking into account the regularly increasing effect of climate change, the current study proposes using an approach based on machine learning methods, which are distinguished by a high degree of autonomy and automation of learning, that is, the ability to self-adapt. The results showed that the error (RMSE) of the model based on the ensemble of regression decision trees due to constant self-adaptation decreased from 4.5 m3/s to 4.0 m3/s and turned out to be lower than the error of a more complex multilayer recurrent neural network (4.9 m3/s). The research results are intended to improve forecasting reliability in the planning, management, and operation of isolated operating power systems. © 2021 The Author(s). The reported study was funded by RFBR, Sirius University of Science and Technology, JSC Russian Railways and Educational Fund “Talent and success”, project number 20-38-51007.

On the basis of literature sources analysis, the paper provides the rationale for the necessity of considering the limited digital devices capabilities when designing closed digital control systems for the complex electrical power grids. The problem of design is decomposed into two subproblems: design of current state observation vector digital transmission systems and current controlled process state estimation; design of digital systems for optimal control vector calculation, transmission and control actions realization. The paper presents consideration of the former problem, i.e. design of current state observation vector digital transmission systems and current controlled process state estimation: the mathematical model of digital system of information transmission and state estimation considering speed and reliability of technical means of implementation is presented; the functional structure of simulation complex is developed; the paper provides the formulation of the problem of estimating the optimal amount of information about the control object state, resulting in a solution of computational experiments simulating complex. © 2021 The Author(s). The reported study was funded by RFBR, Russia, Sirius University of Science and Technology, JSC Russian Railways and Educational Fund “Talent and success”, project number 20-38-51007.

Seasonal fluctuations in electricity consumption, and uneven loading of supply lines reduce not only the energy efficiency of networks, but also contribute to a decrease in the service life of elements of power supply systems. To solve the problem of forecasting power consumption, it is proposed to use the theory of fuzzy sets to assess the effective development of the energy system of the Republic of Tajikistan. According to the statistical data of power consumption for the previous period, a fuzzy logic model with membership functions is proposed, which makes it possible to evaluate consumer satisfaction using the criteria unsatisfactory, satisfactory, conditionally satisfactory, and satisfactory, as well as the efficiency of the consumption mode of compliance using the criteria high, medium, and low, allowing the evaluation of the efficiency plan for the development of the energy system of the Republic of Tajikistan. To obtain and set more accurate data on electricity consumption, calculations were made for the winter period of the year. Based on the proposed calculation model of fuzzy logic, a quantitative component of electricity consumption, the corresponding satisfaction of the consumer, and the efficiency of the regime for nine cities of the Republic of Tajikistan were proposed in the form of diagrams of seasonal electricity consumption. The obtained seasonal power consumption makes it possible to improve the accuracy of estimating power consumption, thereby equalizing the balance of consumption and generation.

The solution of optimization problems is essential for the design and control of technical systems. The optimization problem arising in practice has a high dimension, nonlinear criteria, and constraints. There are a lot of continuous optimization tasks for testing and research of optimization algorithms performance. These tasks have a convex range of acceptable values limited to a specified range for each parameter. The problem of generating test multidimensional continuous optimization tasks with nonlinear constraints and splitting the feasible region is considered. A method was proposed for splitting the feasible region by separate domains using the multidimensional grid of forbidden solutions. As a result, the problem acquires properties closer to optimizing technical systems with complex constraints. The method allows creating an unlimited number of test optimization problems, which can be used to research and develop optimization algorithms. The method is simple to implement, and the impact on the computational complexity of tasks is insignificant. Research has been carried out on four widely used continuous single-objective optimization test functions, with the Genetic algorithm and the Particle Swarm Optimization algorithm. It is shown that the proposed method has an influence on the process of solving multidimensional continuous optimization problems by population algorithms and on the dependence of the accuracy of the algorithm on its heuristic coefficients.

Predicting the variability of wind energy resources at different time scales is extremely important for effective energy management. The need to obtain the most accurate forecast of wind speed due to its high degree of volatility is particularly acute since this can significantly improve the planning of wind energy production, reduce costs and improve the use of resources. In this study, a method for predicting the speed of wind flow in an isolated power system of the Gorno-Badakhshan Autonomous Oblast (GBAO), based on the use of a neural network with a learning process control algorithm, is proposed. Predicting is performed for four seasons of the year, based on hourly retrospective meteorological data of wind speed observations. The obtained wind speed average error forecasting ranged from 20–28% for a day ahead. The prediction results serve as a basis for optimizing the energy consumption of individual generating consumers to minimize their financial and technical costs. In addition, this study takes into account the possibility of exporting electricity to a neighboring country as an additional income line for the isolated GBAO power system during periods of excess energy from hydropower plants (March–September), which is a systematic vision of solving the problem of improving energy efficiency in the conditions of autonomous power supply.

Currently, active networks called microgrids are formed on the basis of local power supply systems with a small share of distributed generation. Microgrids operating in an island mode, in some cases, have the ability to transfer electricity excess to an external network leading to a synchronization requirement; thus, the optimization task in terms of the system’s synchronization must be considered. This paper proposes a method for obtaining synchronization between microgrids and power systems of limited capacity based on a passive synchronization algorithm, allowing us to connect a microgrid to an external power system with a minimum impact moment on the shaft of the generating equipment. The algorithm application was demonstrated by considering a real-life object in Tajikistan. The simulation was carried out on RastrWin3. The obtained results show that the microgrid generator is connected to an external power system at an angle of 0.3◦ and a power surge of 29 kW, unlike the classical synchronization algorithm with an angle of 6.8◦ and a power surge of 154 kW (a reduction of the shock moment by more than five times). The proposed synchronization method allows us to reduce the resource consumption of the generating equipment and increase the reliability and efficiency of the functioning units of the examined power system. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

In recent years, hybrid approaches on population-based algorithms are more often applied in industrial settings. In this paper, we present the approach of a combination of universal, problem-free Swarm Intelligence (SI) algorithms with simple deterministic domain-specific heuristic algorithms. The approach focuses on improving efficiency by sharing the advantages of domain-specific heuristic and swarm algorithms. A heuristic algorithm helps take into account the specifics of the problem and effectively translate the positions of agents (particle, ant, bee) into the problem's solution. And a Swarm algorithm provides an increase in the adaptability and efficiency of the approach due to stochastic and self-organized properties. We demonstrate this approach on two non-trivial optimization tasks: scheduling problem and finding the minimum distance between 3D isomers.

Global digital transformation of the energy sector has led to the emergence of multiple digital platform solutions, the implementation of which have revealed new problems associated with continuous growth of data volumes requiring new approaches to their processing and analysis. This article is devoted to the improper application of machine learning approaches and flawed interpretation of their output at various stages of decision support systems development: data collection; model development, training and testing as well as industrial implementation. As a real industrial case study, the article examines the power generation forecasting problem of photovoltaic power plants. The authors supplement the revealed problems with the corresponding recommendation for industrial specialists and software developers. © 2022 Institute of Advanced Engineering and Science. All rights reserved. The reported study was supported by Russian Foundation for Basic Research RFBR, research project No. 20-010-00911.

The load forecasting of a coal mining enterprise is a complicated problem due to the irregular technological process of mining. It is necessary to apply models that can distinguish both cyclic components and complex rules in the energy consumption data that reflect the highly volatile technological process. For such tasks, Artificial Neural Networks demonstrate advanced performance. In recent years, the effectiveness of Artificial Neural Networks has been significantly improved thanks to new state-of-the-art architectures, training methods and approaches to reduce overfitting. In this paper, the Recurrent Neural Network architecture with a small-size model was applied to the short-term load forecasting of a coal mining enterprise. A single recurrent model was developed and trained for the entire four-year operational period of the enterprise, with significant changes in the energy consumption pattern during the period. This task was challenging since it required high-level generalization performance from the model. It was shown that the accuracy and generalization properties of small-size recurrent models can be significantly improved by the proper selection of the hyper-parameters and training method. The effectiveness of the proposed approach was validated using a real-case dataset. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

In this paper we propose a two-stage lattice Monte Carlo approach for optimization of bimetallic nanoalloys: simulated annealing on a larger lattice, followed by simulated diffusion. Both algorithms are fairly similar in structure, but their combination was found to give significantly better solutions than simulated annealing alone. We also discuss how to tune the parameters of the algorithms so that they work together optimally.

In the paper, the new approach to the scheduling problem are described. The approach deals with the problem of planning the cyclic production and proposes to consider such scheduling problem as the cyclic job-shop problem of the order k, where k is the number of reiterations. It was found out that planning of only one iteration of the loop is less effective than planning of the entire cycle. To the experimental research, a number of test instances of the job-shop scheduling problem by Operation Research Library were used. The Simulated Annealing was applied to solve the instances. The experiments proved that the approach proposed allows increasing the efficiency of cyclic scheduling significantly.

The article considers the problem of the optimal control of a wind power plant based on fuzzy control and automation of generating the fuzzy rule base. Fuzzy rules by experts do not always provide a maximum power output of the wind plant and fuzzy rule bases require an adjustment in the case of changing the parameters of the wind power plant or the environment. This research proposes the method for optimizing the fuzzy rules base compiled by various experts. The method is based on balancing weights of fuzzy rules into the base by the Particle Swarm Optimization algorithm. The experiment has shown that the proposed method allows forming the fuzzy rule base as an exemplary optimal base from a non-optimized set of fuzzy rules. The optimal fuzzy rule base has been taken under consideration for the concrete control loop of wind power plant and the concrete fuzzy model of the wind.

The development of renewable energy and Smart Grid leads to the emergence of prosumers or power generating consumers, which are involved in the processes of bidirectional exchange of electricity and information. The work is devoted to the problem of optimal control of a power generating consumer in Smart Grid. The distinctive research features are the solution of the optimal control problem in conditions of difficult prediction of wind power plant generation, the usage of Swarm Intelligence algorithms to build a system of control rules, and the study of the obtained models on data from two different generating consumers: one on about Russky Island, the second on Popov Island (Far East). We selected a list of priority rules as a decision-making model and applied Particle Swarm Optimization, Bees Algorithm, and Firefly Optimization to build and optimize this model. The computer modeling with the usage of two mounts dataset showed that the proposed approach could significantly increase the revenue of the generating consumers considered.

Deep reactive power compensation allows for reduction of active power losses in transmission lines of power supply systems. The efficiency of the compensation depends on the allocation of reactive power compensation units (RPCUs) at the nodes of a network. In general, investigations devoted to the study of optimal allocation of the compensation units have revealed that it is a static and deterministic optimization problem that can be solved by heuristic methods. However, in real systems, it is reasonable to consider such optimization problems, taking into account the dynamic and stochastic properties of the problems. These properties are the result of equipment failures and operational changes in technical systems. In addition, optimizing the allocation of the compensation units is the NP-hard multifactor problem. Under these circumstances, it is advisable to use the swarm intelligence algorithms. Swarm intelligence is a relatively new approach to solving the optimization problem, which takes inspiration from the behaviour of ants, birds, and other animals. Advantages of swarm algorithms are most evident if problems involve the dynamic or stochastic nature of the objective function and constraints. Contrary to a number of similar studies, this research considers the problem of the optimal allocation of compensation units as a dynamic problem, taking into account the possible random failures of the compensation equipment. The optimization problem has been solved by two Swarm Intelligence algorithms (the Particle Swarm optimization and the Artificial Bee Colony optimization) and Genetic algorithms. It has been aimed at comparing the effectiveness of the algorithms for solving such problems. It was found that swarm algorithms could be successfully applied in the operation control of compensation units in real-time. © 2017 WIT Press.

Recent accidents on roads involving cyclists and autonomous vehicles have raised an alarm in the industry to focus more on cyclist safety. Although there are plenty of datasets publicly available in the industry, they don't include enough instances of cyclists in different road conditions to run comprehensive tests. Therefore, in this work, we present a new publicly available Specialized Cyclist Dataset, which focuses solely on cyclist detection. Our dataset was recorded using a monocular RGB camera in various scenarios experienced by cyclists on roads in Autumn and Winter (with snow) for enabling researchers to run rigorous tests in various conditions. There are 62297 total images, about 18200 cyclists instances, and 30 different cyclists. Additionally in the dataset, we present the Specialized cyclist jersey with a diamond pattern designed specifically for improving detection accuracy compared to street clothes. For convenience, we utilized the popular KITTI labeling format and resolution in addition to Full HD resolution.

The paper considers the problem of optimal control of a prosumer with a wind power plant in smart grid. It is shown that control can be performed in non-deterministic conditions due to the impossibility of accurate forecasting of the generation from renewable plants. A control model based on a priority queue of logical rules with structural-parametric optimization is applied. The optimization problem is considered from a separate prosumer, not from the entire distributed system. The solution of the optimization problem is performed by three swarm intelligence algorithms. Computational experiments were carried out for models of wind energy systems on Russky Island and Popov Island (Far East). The results obtained showed the high effectiveness of the swarm intelligence algorithms that demonstrated reliable and fast convergence to the global extreme of the optimization problem under different scenarios and parameters of prosumers. Also, we analyzed the influence of accumulator capacity on the variability of prosumers. The variability, in turn, affects the increase of the prosumer benefits from the interaction with the external global power system and neighboring prosumers.

The article is devoted to optimization of the reactive power sources arrangement in the industrial power grid to reduce the active power losses in transmission lines and select cross-sections of cable of the lines. To reduce the losses installing of additional reactive power sources in junctions of the grid are proposed. Thus, a problem of the optimal arrangement of the reactive power sources is appeared. This problem was solved by two stochastic optimization algorithms such as the Genetic and the Particle Swarm optimization algorithms. The cost-effectiveness of the suggested method is shown.

The reduction of active power losses in transmission lines of modern power supply systems by solving the problem of reactive power compensation is an important task. The efficiency of the compensation depends on the choice of powers and placement of compensation units in nodes of a network. The task considered is the multi-objective and multi-factor optimization problem, and the time required to solve it increases exponentially with the increase of the dimension of this task. Under these circumstances, it is advisable to use evolutionary and swarm optimization methods. In this paper, two swarm intelligence algorithms have been applied: Artificial Bees Colony optimization and Particle Swarm optimization. Particular attention has been devoted to applying the algorithms in practice, in this case, to solving the problem of the optimal placement of reactive power sources. It has been shown that using a specially developed interface between an optimization algorithm and a model of the optimization problem allows researchers to quickly apply stochastic optimization algorithms. In addition, the influence of the heuristic algorithms parameters of Particle Swarm and Bee Swarm on their effectiveness has been explored. It has been shown that the reactive compensation can reduce the active power losses in the power supply system up to 20%, and the payback period of the installation of the necessary equipment is 2 to 4 years.

Optimization of a power supply system is one of the main directions in power engineering research. The reactive power compensation reduces active power losses in transmission lines. In general, researches devoted to allocation and control of the compensation units consider this issue as a static optimization problem. However, it is dynamic and stochastic optimization problem that requires a real-time solution. To solve the dynamic optimization NP-hard problem, it is advisable to use Swarm Intelligence. This research deals with the problem of the compensation units power control as a dynamic optimization problem, considering the possible stochastic failures of the compensation units. The Particle Swarm Optimization and the Bees Algorithm were applied to solve it to compare the effectiveness of these algorithms in the dynamic optimization of a power supply system.

The issue of electric power grid mode of optimization is one of the basic directions in power engineering research. Currently, methods other than classical optimization methods based on various bio-heuristic algorithms are applied. The problems of reactive power optimization in a power grid using bio-heuristic algorithms are considered. These algorithms allow obtaining more efficient solutions as well as taking into account several criteria. The Firefly algorithm is adapted to optimize the placement of reactive power sources as well as to select their values. A key feature of the proposed modification of the Firefly algorithm is the solution for the multi-objective optimization problem. Algorithms based on a bio-heuristic process can find a neighborhood of global extreme, so a local gradient descent in the neighborhood is applied for a more accurate solution of the problem. Comparison of gradient descent, Firefly algorithm and Firefly algorithm with gradient descent is carried out.