Short-Term Power Load Forecasting Under COVID-19 Based on Graph Representation Learning With Heterogeneous Features

Since 2020, the COVID-19 has spread globally at an extremely rapid rate. The epidemic, vaccination, and quarantine policies have profoundly changed economic development and human activities worldwide. As many countries start to resume economic activities aiming at a “living with COVID” new normal, a short-term load forecasting technique incorporating the epidemic’s effects is of great significance to both power system operation and a smooth transition. In this context, this paper proposes a novel short-term load forecasting method under COVID-19 based on graph representation learning with heterogeneous features. Unlike existing methods that fit power load data to time series, this study encodes heterogeneous features relevant to electricity consumption and epidemic status into a load graph so that not only the features at each time moment but also the inherent correlations between the features can be exploited; Then, a residual graph convolutional network (ResGCN) is constructed to fit the non-linear mappings from load graph to future loads. Besides, a graph concatenation method for parallel training is introduced to improve the learning efficiency. Using practical data in Houston, the annual, monthly, and daily effects of the crisis on power load are analyzed, which uncovers the strong correlation between the pandemic and the changes in regional electricity utilization. Moreover, the forecasting performance of the load graph-based ResGCN is validated by comparing with other representative methods. Its performance on MAPE and RMSE increased by 1.3264 and 15.03%, respectively. Codes related to all the simulations are available on https://github.com/YoungY6/ResGCN-for-Short-term-power-load-forecasting-under-COVID-19.

Identification and Stochastic Optimizing the UAV Motion Control in Turbulent Atmosphere

In a class of diffusion Markov processes, we formulate a problem of identification of nonlinear stochastic dynamic systems with random parameters, multiplicative and additive noises, control functions, and the state vector at a final time moment. For such systems, the identifiability conditions are being studied, and necessary conditions are formulated in terms of the general theory of extreme problems. The developed engineering methods for identification and optimizing nonlinear stochastic systems are presented as well as their application for unmanned aerial vehicles under wind disturbances caused by atmospheric turbulence, namely, for optimizing the autopilot parameters during a rotary maneuver of an unmanned aerial vehicle in translational motion, taking into account the identification of its angular velocities.

Gisola: A High-Performance Computing Application for Real-Time Moment Tensor Inversion

Automatic moment tensor (MT) determination is essential for real-time seismological applications. In this article, Gisola, a highly evolved software for MT determination, oriented toward high-performance computing, is presented. The program employs enhanced algorithms for waveform data selection via quality metrics, such as signal-to-noise ratio, waveform clipping, data and metadata inconsistency, long-period disturbances, and station evaluation based on power spectral density measurements in parallel execution. The inversion code, derived from ISOLated Asperities—an extensively used manual MT retrieval utility—has been improved by exploiting the performance efficiency of multiprocessing on the CPU and GPU. Gisola offers the ability for a 4D spatiotemporal adjustable MT grid search and multiple data resources interconnection to the International Federation of Digital Seismograph Networks Web Services (FDSNWS), the SeedLink protocol, and the SeisComP Data Structure standard. The new software publishes its results in various formats such as QuakeML and SC3ML, includes a website suite for MT solutions review, an e-mail notification system, and an integrated FDSNWS-event for MT solutions distribution. Moreover, it supports the ability to apply user-defined scripts, such as dispatching the MT solution to SeisComP. The operator has full control of all calculation aspects with an extensive and adjustable configuration. MT’s quality performance, for 531 manual MT solutions in Greece between 2012 and 2021, was measured and proved to be highly efficient.

Supervised linear classification of Gaussian spatio-temporal data

In this article we focus on the problem of supervised classifying of the spatio-temporal Gaussian random field observation into one of two classes, specified by different mean parameters. The main distinctive feature of the proposed approach is allowing the class label to depend on spatial location as well as on time moment. It is assumed that the spatio-temporal covariance structure factors into a purely spatial component and a purely temporal component following AR(p) model. In numerical illustrations with simulated data, the influence of the values of spatial and temporal covariance parameters to the derived error rates for several prior probabilities models are studied.

ПОНЯТТЯ ЧАСУ В ПОЕЗІЇ РАБІНДРАНАТА ТАГОРА: ЧИТАЦЬКА ІНТЕРПРЕТАЦІЯ

In the current study, readers’ interpretation of the conception of time in Rabindranath Tagore’s nonnarrative poetry is approached from the perspective of schema theory (E. Semino) and Text World Theory (P. Werth, J. Gavins). The analysis shows that in Rabindranath Tagore’s non-narrative poems about time, which were written in or translated into English, a TIME schema is instantiated through (i) linguistic units that refl ect human idea of dividing time into conventional periods – moments, days, months, years, etc.; (ii) a complex web of fi gurative devices, metaphors and similes in particular. In readers’ minds, fi gurative language prompts associative connections between several core, or basic, schemata: TIME, GOD, HUMAN LIFE, LIFE OF NATURE. Basic schemata can contain subordinate ones (TIME: MOMENT, DAY, MONTH; GOD: THY HANDS, SHUT GATE (thy gate be shut); HUMAN LIFE: CLOCK, PARODY, POEM, MEMORY; LIFE OF NATURE: BUTTERFLY, GARDEN, FLOWER, etc.). Connections between schemata on either a level or across levels indicate that the abstract conception of time is objectifi ed through physical processes and entities, which are perceptible by human senses; and that human life and life of nature have some common characteristics determined by time-related processes. Relying on schemata instantiated by the language of a poem, a reader creates his or her mental representation of the text, in other words, builds a poem’s text-world. On the text-world level, the conception of time in Rabindranath Tagore’s non-narrative poetry is presented through the use of all the three types of elements from which text-worlds are constructed: temporal deictic markers (world-building elements), function-advancing propositions (elements that describe actions, events, and states), and intensive relational processes (elements which describe physical characteristics). Text-worlds in Rabindranath Tagore’s non-narrative poems about time can be complex. His texts can contain world-switches – changes in the temporal parameters “present – future” from the perspective of the author and “present – past” from the perspective of a reader, and/or modal worlds that exist as hypothetical ones in the minds of the author and his readers. The latter concerns the poems in which time is associated with the transcendent conception of God. Key words: Rabindranath Tagore, non-narrative poetry, time, schema, text-world.

Response-Only Parametric Estimation of Structural Systems Using a Modified Stochastic Subspace Identification Technique

The present paper is a study of output-only modal estimation based on the stochastic subspace identification technique (SSI) to avoid the restrictions of well-controlled laboratory conditions when performing experimental modal analysis and aims to develop the appropriate algorithms for ambient modal estimation. The conventional SSI technique, including two types of covariance-driven and data-driven algorithms, is employed for parametric identification of a system subjected to stationary white excitation. By introducing the procedure of solving the system matrix in SSI-COV in conjunction with SSI-DATA, the SSI technique can be efficiently performed without using the original large-dimension data matrix, through the singular value decomposition of the improved projection matrix. In addition, the computational efficiency of the SSI technique is also improved by extracting two predictive-state matrixes with recursive relationship from the same original predictive-state matrix, and then omitting the step of reevaluating the predictive-state matrix at the next-time moment. Numerical simulations and experimental verification illustrate and confirm that the present method can accurately implement modal estimation from stationary response data only.

ONGOING FOLLOW-UP NEA OBSERVATIONS IN UKRAINE AND CHINA USING RDS CCD TECHNIQUE

The current state of near-Earth asteroids (NEAs) observations shows an annual increase in the number of newly discovered objects However, the frequency distribution of NEAs by size shows a sharp decrease in the number of objects with size less than 300 m, which contradicts the results of theoretical modeling of the NEA population. Considering definition of potentially hazardous asteroids (PHA), only objects with diameters more than 140 m could pose catastrophic consequences to the Earth and mankind in general. But in the same time, impacts of smaller size objects could lead to significant consequences on local level and their large predicted number increases this probability. Due to their small size which results in faint apparent magnitude, such NEAs are discovered in a short interval of their close approach (CA) to the Earth, when their apparent magnitude are tending to be as bright as possible for a given size. This is not only facilitates the detection of such new objects but also increases their observability by small ground-based telescopes. However, apparent rate of motion during this time might exceed 10 deg d −1 making the observations challenging. The used Rotating-drift-scan CCD (RDS CCD) technique allows to get images of fast-moving objects as a point, that in turn to determine the coordinates of their image centers with sufficient astrometric precision. Obtained in current research project positions show errors in the range ± (0.2″ − 0.3″) in both coordinates with comparison both to JPL's HORIZONS 1 system and NEODyS-2 2 service. The part of observations was obtained around time moment of minimal distance to the Earth during current CA for newly discovered NEAs. Such observations are important to extend observed orbital arc for reliable improvement of their orbit determinations and reducing orbital uncertainty, so it will be possible to recover them in next apparitions.

Set-Valued Uncertain Process: Definition and Some Properties

Some phenomena are developing over time, while they are uncertain sets at each moment. From an uncertain set, we mean an unsharp concept, such as “illness” and “recovery”, that is not exactly clear, even for an expert. The values of a parameter that are considered “recovery” would guide one to explain the underlying concept quantitatively. For instance, in recovering from some disease, different levels of health might be assumed. Particularly, at each specific time moment, being healthy to some degree would be measured by belonging parameter values to a set of numbers with a specific belief degree. This set might be extracted using imprecisely observed data, while an expert opinion completely expresses the belief degree. Such concepts would direct one to employ uncertainty theory as a strong axiomatic mathematical framework for modeling human reasoning. Another important feature of these sets is their variation over time. For instance, the set defining “recovery” at the beginning stage of recovery in a disease would be completely or partially different from that at other stages. These characteristics result in considering a sequence of evolving sets over time. Analyzing the behavior of such a sequence motivated us to define the set-valued uncertain process. This concept is a combination of uncertain set, uncertain process, and uncertain sequence. Here, we introduce the main concept. Some properties are extracted and clarified, along with some illustrative examples.

On the construction of resolving control in the problem of getting close at a fixed time moment

The problem of getting close of a controlled system with a compact space in a finite-dimensional Euclidean space at a fixed time is studied. A method of constructing a solution to the problem is proposed which is based on the ideology of the maximum shift of the motion of the controlled system by the solvability set of the getting close problem.