فصلنامه روشهای هوشمند در صنعت برق
پیاپی 56 (زمستان 1402)

Electrical load forecasting is the prediction of future demands based on various data and factors containing different consumptions on weekdays, electricity prices and weather conditions that are different for societies and places. Generally, medium-term electrical load forecasting is often used for the operation of thermal and hydropower plants, optimal time planning for maintenance of power plants and the power grids. However, long-term electrical load forecasting is used to manage on-time future demands and generation, transmission and distribution expansion planning. In this paper, a hybrid long-term load forecasting approach using wavelet transform and an outlier robust extreme learning machine is proposed. Hourly load and temperature data were extracted from the GEFCOM 2014 database and divided into two classes of training and test. The one-level wavelet transform is used to decompose data to extract properties and reduce the dimensions of the data matrix. Decomposed low-frequency component (approximations) and high-frequency component values (details) from wavelet analysis are entered into the model for training and forecasting. For comparison accuracy of the proposed method, wavelet transform is applied to the data for the other three extreme learning machines. Also data without wavelet transform entered into four other forecasting models and the load forecasting results are compared with the proposed method. The results of the above mentioned evaluation show that electrical load forecasting by using wavelet transform and outlier robust extreme learning machine improves forecasting accuracy and the MAPE reduces to 3.0966. The overall calculated error by the proposed method was the best result obtained between the three several models of extreme learning machines and without preprocessing model. The MAPE is 0.4208 less than the ELM, 0.944 less than the RELM, and 0.1353 less than the WRELM model, respectively.

Since integration of solar photovoltaic (PV) sources into the power grid is increasing rapidly in recent years, the capability of photovoltaic source inverters can be an opportunity to improve the technical and economic indicators via reactive power management in low voltage distribution networks grids. This work proposes an optimal planning model to improve the voltage deviation index and increase the revenue sale electricity with the capability of PV inverters and fixed capacitors. In this regard, the optimal capacity of the PV inverter is determined simultaneously with the location and number of fixed capacitors to minimize investment (for PV inverter, fixed capacitor, operating cost) and maximize electricity sales revenue. For this purpose, an innovative model is presented that is able to calculate the annual technical-economic evaluation. To make the costs for investment, operation and maintenance of compensating devices more realistic, the lifespan and additional cost of inverter oversizing in the objective function are modelled. In this article, load flow equations along with technical constraints are integrated into a mixed-integer second-order conic programming model. Two real grids were simulated using MATLAB software in order to show the effectiveness of the proposed model. The comparison of the proposed RPM method with conventional methods confirmed considerable reduction of investment and energy losses in the low voltage distribution networks grids.

Electrical load modeling has been considered an essential task in power system studies. With the recent development of power systems, load modeling is becoming more and more challenging. The previous methods on load modeling are suffered from: i) high sensitivity to noise; ii) neglecting the load correlation in a power system, iii) high computational burden, and iv) dependency on the local measurement devices. To address these problems, this paper develops a deep neural network-based structure that can identify a large number of parameters simultaneously with fast performance as well as high accuracy. The designed network can fully understand the temporal features using a gated recurrent neural network-based structure. Furthermore, to provide the ability to estimate a large number of load parameters, a technique to assign the learning weight has been developed. Consequ ently, to enhance the robustness of the designed network considering noisy conditions, a loss function has been developed in this paper. The numerical results on the IEEE 68-bus system demonstrate the effectiveness and superiority of the proposed network in comparison with several shallow-based and deep-based structures.

In this paper, a dynamic mutant version of the gray wolf optimization algorithm (MGWO) is proposed to solve the economic-environmental dispatch (E-ED) problem of a standard 40-unit power system with two wind farms. Thus, a comprehensive objective function of operating costs is presented, which is a combination of wind energy costs, over-estimated penalty costs, under-estimated penalty costs, thermal unit costs and emission costs. Due to the random nature of wind speed, the power generated by wind turbines is unpredictable. Therefore, the Weibull probability distribution function has been used to model the wind farm power in this paper. The cost of operating a wind farm is considered probabilistic so that low-probability wind scenarios have less effect on the total operation cost. The simulations are performed in the form of three section and the optimization results are compared with several meta-heuristic algorithm results for validation. The results of the optimizations in all three scenarios and its comparison with other algorithms confirm the better performance and higher accuracy of the proposed MGWO algorithm than the original version of the gray wolf algorithm (GWO) as well as other algorithms.

Self-Healing is the most essential feature for smart distribution network Restoration when a fault occurs. Islanding of the fault zone can be done both offline and online. Using the online islanding method to restoration the service in the fault zone, the boundary of islanding micro-grids and the number of islands can be determined optimally during the fault. In this study, a novel two-step mathematical method for self-healing restoration after the fault is presented. In the first layer, the optimal arrangement of the system in the faulty area is determined by a new mathematical model. In the first layer, the boundary of island-operating MGs is determined after the fault, which leads to decreasing load shedding and operation costs of the distribution system. Then, in the second layer, the unit commitment problem in the smart distribution system is solved. The load shedding or outage, non-dispatchable distributed generation (DG) resources rescheduling, and optimal planning energy storage systems (ESSs) are determined. Low execution time and the optimal solution are the most essential advantages of the pro po s ed scheme. Tools such as smart load shedding and demand response Programs (DRP) have also been used for optimal system restoration. The IEEE 33-bus distribution system is used to validate the prop osed method. The results of case studies demonstrate the effectiveness of the proposed methodology.

In this paper, a three-level scenario-based framework for determining the optimal strategy and planning of microgrids located in a 118-bus distribution system is presented. This paper considers the uncertai nties of renewable energy resources, load demand, and the charge / discharge schedule of electric vehicles. In order to increase planning flexibility, the operator will be able to change the flow through the distribution feeder reconfiguration. Also in the proposed model, customers will be able to reduce their costs by participating in a demand response program. In the first level of the proposed model, the bidding strategy of microgrids is determined. In the second level, the market clearing price is determined by the independent system operator and according to the submitted bids. Finally, in the third stage, the problem of final microgrid programming is solved by a participatory game theory method. The proposed model is solved by the CPLEX solver in GAMS software and the results show that the dynamic topology improves the planning flexibility and thus reduces the total operating cost by about 10%. The results also show that the coordination of electric vehicles with scheduling, the presence of storage systems and the implementation of the demand response program leads to a significant reduction in the level of market-clearing price and thus reduce operating costs.

It is essential to control vital variables in patients whose natural control system has been compromised for some reason. One of these vital variables is blood glucose levels. Unfortunately, in people with diabetes (blood sugar), blood glucose levels are not regulated properly. To compensate for this lack, in recent years, several studies and efforts have been made to build and improve the function of the artificial pancreas to control blood sugar. The presence of factors such as multiple uncertainties due to physiological differences in individuals, various activities during the day, delayed effects of carbohydrates on blood sugar levels, stress and exercise make controlling the artificial pancreas a challenging system. But one of the most important challenges in this area, which has not been less addressed in the literature is the limitation on the allowable dose of insulin injected into the artificial pancreas for patients with type 1 diabetes. On the one hand, injecting a high dose of insulin can cause problems such as hyperglycemia issues and on the other hand, injecting a negative dose of insulin is meaningless. In this paper, after selecting the Bergman model and considering the existence of asymmetric saturation in the actuator, the back-stepping control method is used and it is combined with an adaptive technique to improve the controller performance. Finally, simulation results depict that in the presence of large step disturbance, the insulation rate remains in the allowed band of zero to 20 mU/min, and the blood glucose level does not exceed the appropriate level 130mg/dl.

Given the importance of reducing data latency in discrete wireless networks in critical situations, we present the combined routing protocol with a storage and forwarding approach in Throw-Box-based network topology concerning aspects such as proper relay prediction and effective buffer management. To reduce the data transfer time in the relay node selection criteria, we consider the effect of different factors: node records, end-to-end latency, the nodes' available buffer space, and information such as average speed and node movement direction. We also use artificial intelligence to perform optimal routing using the Simulated Annealing algorithm. Important common performance criteria such as average latency, delivery ratio, number of lost messages, and network overhead were used to evaluate the performance of the proposed model. The results showed that our proposed routing method has less reception delay than other routing methods and maintains maximum transmission.

Gearbox and vibrations are two inseparable components of each other. In other words, the nature of the gear meshing in the gearbox has inevitable vibrations due to the impact during the meshing of the teeth. These unavoidable vibrations in some cases cause the gearbox to malfunction, so vibration analyzes are very important and efficient in analyzing gearbox performance and optimizing them. A planetary gearbox has a main gear of the sun as the actuator in the center, several planetary gears around it and a ring gear in which this set rotates and an arm is attached to the planetary gears and acts as the output for the planetary gearbox. In this paper, first to express the desired vibration relations in the planetary gearbox. Then to investigate and apply the relations governing the electric motor in MATLAB software. In the following, the vibration model of the planetary gearbox motor coupling model is simulated in order to observe and analyze the interaction between the electric motor and the planetary gearbox. Frequency spectrum are analyzed to investigate the interaction of motor and planetary gearbox. It should be noted that dynamic modeling and analysis has been performed in ABAQUS software to extract the mesh stiffness of time-varying engagement between the teeth of the two gears involved in the planetary gearbox.

In recent years, attention to renewable energy and distributed generation has increased due to increased energy demand and environmental pollution. To this end, in the new power grid structure, consumers can also play a producer role. Considering that the number of prosumers in this structure is much more than traditional power networks, the need for a secure, transparent, fast, scalable platform for energy exchanges has greatly increased. Blockchain technology can provide such a platform due to its unique properties. Although there are many blockchain-based platforms in different countries in enregy field, but in Iran there is no such platform. Therefore, the main purpose of this paper is to design and implement a local pilot platform for peer-to-peer blockchain-based energy exchange, taking into account the specific conditions of Iran's electricity grid. The macro platform architecture is designed based on the concept of Minimum Viable Product (MVP) considering functional and non-functional requirements in the form of unified modeling language (UML) diagrams. The proposed platform pilot has been implemented in the form of 4 main elements including smart contract, user interface, blockchain platform, and blockchain and non-blockchain databases and has been evaluated and tested using different scenarios. These tests mainly include the unit test and the integrity test, which were successfully performed on the platform. This platform has been designed and implemented for the first time in Iran in accordance with the Ethereum protocol and based on microservice architecture. In addition to the ability to integrate with Ethereum-based systems, this platform is scalable due to its modular design.