A quantitative risk assessment model involving frequency and threat degree under line-of-business services for infrastructure of emerging sensor networks
Description:
Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.
Description:
Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.
Description:
This paper addresses the planning problem of residential micro combined heat and power (micro-CHP) systems (including micro-generation units, auxiliary boilers, and thermal storage tanks) considering the associated technical and economic factors. Since the accurate values of the thermal and electrical loads of this system cannot be exactly predicted for the planning horizon, the thermal and electrical load uncertainties are modeled using a two-stage adaptive robust optimization method based on a polyhedral uncertainty set. A solution method, which is composed of column-and-constraint generation (C&CG) algorithm and block coordinate descent (BCD) method, is proposed to efficiently solve this adaptive robust optimization model. Numerical results from a practical case study show the effective performance of the proposed adaptive robust model for residential micro-CHP planning and its solution method.
Description:
This study presents a reliability-constrained adaptive-robust multi-resolution model for generation maintenance scheduling (GMS) problem considering the uncertainty sources of electricity demand, wind power generation, and equipment unavailabilities. In the proposed tri-level adaptive-robust model, a polyhedral uncertainty set is used to model the electricity demand and wind power generation fluctuations. In addition, equipment unavailabilities as discrete uncertainty sources are modelled in the reliability sub-problem where the expected energy not supplied is determined as a reliability criterion. Accordingly, the proposed model obtains a robust maintenance schedule for generating units immunised against the worst realisation of electricity demand and wind power generation while satisfying the reliability constraint considering equipment unavailabilities. Moreover, maintenance and operation periods are specifically modelled using different resolutions in the proposed multi-resolution GMS approach. To solve the proposed reliability-constrained adaptive-robust multi-resolution model, a new solution approach including Benders cut, reliability cut, and block coordinate descent method is presented. Numerical results on two test systems show the effectiveness of both the proposed GMS model and the proposed solution approach.
Description:
This letter proposes a model for tracking the equilibrium point of the real-time locational marginal price (LMP) based residential demand response program, where elastic demand is modeled as a monotonously decreasing linear function of the LMP. The resulting bi-level model contains both primary and dual variables, making it difficult to solve. Using duality, the dual model is formulated as a convex quadratic problem which is tractable to solve and find the global optimum. Furthermore, the condition for the existence of the equilibrium point is given. Numerical results on the IEEE 30-bus system verifies the effectiveness of the demand response model.
Description:
Summary This paper presents a stochastic multiobjective model for generation maintenance scheduling (GMS) problem and a solution method to solve it. The proposed model properly considers both competing objectives and uncertainty sources of GMS problem. Three competing objective functions including total cost, risk measure, and total emission are simultaneously minimized in the proposed model. Moreover, forced outages of generating units throughout the GMS horizon are characterized by externally generated scenarios. Stochastic programming as an efficient approach to model uncertainty sources has been used in the proposed stochastic multiobjective GMS. Augmented normalized normal constraint (A‐NNC) method is developed as an efficient multiobjective mathematical programming approach to obtain Pareto optimal solutions for the proposed model. Further, a stochastic decision maker based on out‐of‐sample analysis is suggested to find the most preferred solution for GMS problem. The IEEE 118‐bus test system is used to investigate the effectiveness of the proposed model and solution method.
Description:
In mature electric power systems, growth in generation/demand, integration of renewable energy, and system expansion may elevate short-circuit levels beyond the rating of existing components. Thanks to technological advancements in materials, superconducting fault current limiters (SFCLs) can effectively alleviate excessive fault currents without affecting normal operation of power systems as they are invisible in non-faulted conditions. However, due to their rather high prices, SFCL optimal placement (SOP) comes to attention. The effectiveness of SOP depends on optimally siting of SFCL resistive/inductive types, which vary in transmission and distribution networks due to different X/R ratios. In this study, an SOP is proposed to determine optimal locations and types of SFCLs taking into account short-circuit level of buses. In addition, a complex-valued artificial bee colony (CABC) algorithm is introduced to efficiently solve complex-valued optimisation problems such as power system applications, including SOP. The proposed SOP with CABC is examined on transmission and distribution test cases to evaluate its effectiveness. It is found that by employing the proposed complex decision vector, the CABC algorithm exhibits an enhanced exploration capability and convergence rate due to halving decision vector length and considering mutual effects of real and imaginary parts of decision variables.
Description:
This paper presents a new robust self-scheduling strategy for virtual power plants (VPPs) considering the uncertainty sources of electricity prices, wind generations, and loads. Multi-horizon information-gap decision theory (MH-IGDT) as a non-deterministic and non-probabilistic uncertainty modeling framework is proposed here to specifically model the uncertainty sources considering their various uncertainty horizons. Since each uncertain parameter tends to optimize its uncertainty horizon competitively for a particular value of the uncertainty budget, the proposed MH-IGDT model is formulated as a multi-objective optimization problem. To solve this multi-objective problem, enhanced normalized normal constraint (ENNC) method is presented, which can obtain efficient uniformly-distributed Pareto optimal solutions. The proposed ENNC includes augmented normalized normal constraint method and lexicographic optimization technique to enhance the search performance in the objective space. To address the unsolved issue of being risk-averse or risk-seeker for a VPP in the market, a bi-directional decision-making approach is presented. This decision maker comprises an ex-ante performance evaluation method and a forward-backward dynamic programming approach to hourly find the best Pareto solution within the generated risk-averse and risk-seeker Pareto frontiers. Simulation results of the proposed self-scheduling strategy are presented for a VPP including dispatchable/non-dispatchable units, storages, and loads.