Search

This study forecasts electricity consumption in a smart grid environment. We present a bottom-up prediction method using a combination of forecasting values based on time-series clustering using advanced metering infrastructure (AMI) data, one of the core smart grid technologies. Remote data metering every 15 min to 1 h is possible with real-time communication on power generation information, consumption, and AMI development. Hence, its prediction is more challenging due to the large variation of each household’s electricity. These issues were solved by time-series clustering methods using Euclidean distances and Dynamic Time Warping distance. The auto-regressive integrated moving average (ARIMA), ARIMA exogenous (ARIMAX), double seasonal Holt–Winters (DSHW), trigonometric, Box–Cox transform, autoregressive moving average errors, trend and seasonal components (TBATS), neural network nonlinear autoregressive (NNAR), and nonlinear autoregressive exogenous (NARX) models were used for demand forecasting based on clustering. The result showed that the time-series clustering method performed better than that using the total amount of electricity demand regarding the mean absolute percentage error and root mean squared error.Hence, various exogenous variables were considered to improve model accuracy. The model considering exogenous variables—cooling degree day, humidity, insolation, indicator variables, and generation power consumption performed better than that without exogenous variables.

The renewable energy industry is rapidly expanding due to environmental pollution from fossil fuels and continued price hikes. In particular, the solar energy sector accounts for about 48.7% of renewable energy, at the highest production ratio. Therefore, climate prediction is essential because solar power is affected by weather and climate change. However, solar radiation, which is most closely related to solar power, is not currently predicted by the Korea Meteorological Administration; therefore, solar radiation prediction technology is needed. In this study, we predict solar radiation using extra-atmospheric solar radiation and three weather variables: temperature, relative humidity, and total cloud volume. We compared the performance of single models of machine and deep learning in previous work. For the single-model comparison, we used boosting techniques, such as extreme gradient boosting and categorical boosting (CatBoost) in machine learning, and the recurrent neural network (RNN) family (long short-term memory and gated recurrent units). In this paper, we compare CatBoost (previously the best model) with CNN and present a CNN-CatBoost hybrid model prediction method that combines CatBoost in machine learning and CNN in deep learning for the best predictive performance for a single-model comparison. In addition, we checked the accuracy change when adding wind speed and precipitation to the hybrid model. The model that considers wind speed and precipitation improved at all but three (Gangneung, Suwon, and Cheongju) of the 18 locations.

Regional accuracy was examined using extreme gradient boosting (XGBoost) to improve frost prediction accuracy, and accuracy differences by region were found. When the points were divided into two groups with weather variables, Group 1 had a coastal climate with a high minimum temperature, humidity, and wind speed and Group 2 exhibited relatively inland climate characteristics. We calculated the accuracy in the two groups and found that the precision and recall scores in coastal areas (Group 1) were significantly lower than those in the inland areas (Group 2). Geographic elements (distance from the nearest coast and height) were added as variables to improve accuracy. In addition, considering the continuity of frost occurrence, the method of reflecting the frost occurrence of the previous day as a variable and the synthetic minority oversampling technique (SMOTE) pretreatment were used to increase the learning ability.

Peak load demand forecasting is important in building unit sectors, as climate change, technological development, and energy policies are causing an increase in peak demand. Thus, accurate peak load forecasting is a critical role in preventing a blackout or loss of energy. This paper presents a study forecasting peak load demand for an institutional building in Seoul. The dataset were collected from campus area consisting of 23 buildings. ARIMA models, ARIMA-GARCH models, multiple seasonal exponential smoothing, and ANN models are used. We find an optimal model with moving window simulations and step-ahead forecasts. Also, including weather and holiday variables is crucial to predict peak load demand. The ANN model with external variables (NARX) worked best for 1-h to 1-d ahead forecasting. Keywords: Peak load demand forecasting, Institutional building, Time series, ARIMA, GARCH, ANN

This study was conducted to investigate the applicability of measuring internet traffic as an input of short-term electricity demand forecasts. We believe our study makes a significant contribution to the literature, especially in short-term load prediction techniques, as we found that Internet traffic can be a useful variable in certain models and can increase prediction accuracy when compared to models in which it is not a variable. In addition, we found that the prediction error could be further reduced by applying a new multivariate model called VARX, which added exogenous variables to the univariate model called VAR. The VAR model showed excellent forecasting performance in the univariate model, rather than using the artificial neural network model, which had high prediction accuracy in the previous study.

This study compared the methods used to forecast increases in power consumption caused by the rising popularity of electric vehicles (EVs). An excellent model for each region was proposed using multiple scaled geographical datasets over two years. EV charging volumes are influenced by various factors, including the condition of a vehicle, the battery’s state-of-charge (SOC), and the distance to the destination. However, power suppliers cannot easily access this information due to privacy issues. Despite a lack of individual information, this study compared various modeling techniques, including trigonometric exponential smoothing state space (i.e., Trigonometric, Box–Cox, Auto-Regressive-Moving-Average (ARMA), Trend, and Seasonality (TBATS)), autoregressive integrated moving average (ARIMA), artificial neural networks (ANN), and long short-term memory (LSTM) modeling, based on past values and exogenous variables. The effect of exogenous variables was evaluated in macro- and micro-scale geographical areas, and the importance of historic data was verified. The basic statistics regarding the number of charging stations and the volume of charging in each region are expected to aid the formulation of a method that can be used by power suppliers.

This study forecasts electricity demand in a smart grid environment. We present a prediction method that uses a combination of forecasting values based on time-series clustering. The clustering of normalized periodogram-based distances and autocorrelation-based distances are proposed as the time-series clustering methods. Trigonometrical transformation, Box–Cox transformation, autoregressive moving average (ARMA) errors, trend and seasonal components (TBATS), double seasonal Holt–Winters (DSHW), fractional autoregressive integrated moving average (FARIMA), ARIMA with regression (Reg-ARIMA), and neural network nonlinear autoregressive (NN-AR) are used for demand forecasting based on clustering. The results show that the time-series clustering method performs better than the method using the total amount of electricity demand in terms of the mean absolute percentage error (MAPE).

Purpose: Primary central nervous system (CNS) gliomas can be classified by characteristic genetic alterations. In addition to solid tissue obtained via surgery or biopsy, cell-free DNA (cfDNA) from cerebrospinal fluid (CSF) is an alternative source of material for genomic analyses., Experimental Design: We performed targeted next-generation sequencing of CSF cfDNA in a representative cohort of 85 patients presenting at two neurooncological centers with suspicion of primary or recurrent glioma. Copy-number variation (CNV) profiles, single-nucleotide variants (SNV), and small insertions/deletions (indel) were combined into a molecular-guided tumor classification. Comparison with the solid tumor was performed for 38 cases with matching solid tissue available., Results: Cases were stratified into four groups: glioblastoma (n = 32), other glioma (n = 19), nonmalignant (n = 17), and nondiagnostic (n = 17). We introduced a molecular-guided tumor classification, which enabled identification of tumor entities and/or cancer-specific alterations in 75.0% (n = 24) of glioblastoma and 52.6% (n = 10) of other glioma cases. The overlap between CSF and matching solid tissue was highest for CNVs (26%-48%) and SNVs at predefined gene loci (44%), followed by SNVs/indels identified via uninformed variant calling (8%-14%). A molecular-guided tumor classification was possible for 23.5% (n = 4) of nondiagnostic cases., Conclusions: We developed a targeted sequencing workflow for CSF cfDNA as well as a strategy for interpretation and reporting of sequencing results based on a molecular-guided tumor classification in glioma. See related commentary by Abdullah, p. 2860., (©2024 The Authors; Published by the American Association for Cancer Research.)

The chemokine CXCL12 promotes glioblastoma (GBM) recurrence after radiotherapy (RT) by facilitating vasculogenesis. Here we report outcomes of the dose-escalation part of GLORIA (NCT04121455), a phase I/II trial combining RT and the CXCL12-neutralizing aptamer olaptesed pegol (NOX-A12; 200/400/600 mg per week) in patients with incompletely resected, newly-diagnosed GBM lacking MGMT methylation. The primary endpoint was safety, secondary endpoints included maximum tolerable dose (MTD), recommended phase II dose (RP2D), NOX-A12 plasma levels, topography of recurrence, tumor vascularization, neurologic assessment in neuro-oncology (NANO), quality of life (QOL), median progression-free survival (PFS), 6-months PFS and overall survival (OS). Treatment was safe with no dose-limiting toxicities or treatment-related deaths. The MTD has not been reached and, thus, 600 mg per week of NOX-A12 was established as RP2D for the ongoing expansion part of the trial. With increasing NOX-A12 dose levels, a corresponding increase of NOX-A12 plasma levels was observed. Of ten patients enrolled, nine showed radiographic responses, four reached partial remission. All but one patient (90%) showed at best response reduced perfusion values in terms of relative cerebral blood volume (rCBV). The median PFS was 174 (range 58-260) days, 6-month PFS was 40.0% and the median OS 389 (144-562) days. In a post-hoc exploratory analysis of tumor tissue, higher frequency of CXCL12 + endothelial and glioma cells was significantly associated with longer PFS under NOX-A12. Our data imply safety of NOX-A12 and its efficacy signal warrants further investigation., (© 2024. The Author(s).)

H3K27M, a driver mutation with T and B cell neoepitope characteristics, defines an aggressive subtype of diffuse glioma with poor survival. We functionally dissect the immune response of one patient treated with an H3K27M peptide vaccine who subsequently entered complete remission. The vaccine robustly expanded class II human leukocyte antigen (HLA)-restricted peripheral H3K27M-specific T cells. Using functional assays, we characterized 34 clonally unique H3K27M-reactive T cell receptors and identified critical, conserved motifs in their complementarity-determining region 3 regions. Using detailed HLA mapping, we further demonstrate that diverse HLA-DQ and HLA-DR alleles present immunogenic H3K27M epitopes. Furthermore, we identified and profiled H3K27M-reactive B cell receptors from activated B cells in the cerebrospinal fluid. Our results uncover the breadth of the adaptive immune response against a shared clonal neoantigen across multiple HLA allelotypes and support the use of class II-restricted peptide vaccines to stimulate tumor-specific T and B cells harboring receptors with therapeutic potential.

Background: Gliomas represent the most frequent malignant primary brain tumors in adults. Despite multimodal treatment concepts involving surgery, irradiation and chemotherapy, the prognosis remains poor and they are incurable. Recent insights into the interactions between the immune system and the central nervous system as well as breakthroughs in the results of other cancer types have led to the fact that various immunotherapeutic approaches against gliomas have also been investigated and in some cases specifically developed., Objective: This article provides an overview of the current status of different immunotherapeutic concepts against gliomas, highlighting the advantages, disadvantages, and challenges. Additionally, it provides an overview of currently ongoing immunotherapeutic clinical trials in Germany and neighboring countries., Results: Previous randomized studies on antibodies against programmed cell death protein 1 (anti-PD1) immune checkpoint inhibition, viral treatment and peptide vaccination targeting the variant III of the epidermal growth factor receptor (EGFRvIII) in glioblastomas were negative with respect to survival benefits. Conversely, other immunotherapeutic approaches, such as multivalent or driver mutation-based vaccinations, cytokine-based therapy and cell therapy, demonstrated a robust scientific foundation, with at least early studies showing promising safety and pharmacodynamic effects on the tumors., Discussion: Currently, immunotherapies against gliomas should only be applied within the framework of well-designed clinical studies. There are still many knowledge gaps regarding the mechanisms of action and resistance of various immunotherapies. Accompanying translational research is essential to address these gaps and develop more effective therapies., (© 2023. The Author(s).)

Background: Concurrent malignant brain tumors in patients with multiple sclerosis (MS) constitute a rare but paradigmatic phenomenon for studying neuroimmunological mechanisms from both molecular and clinical perspectives., Methods: A multicenter cohort of 26 patients diagnosed with both primary brain tumors and multiple sclerosis was studied for disease localization, tumor treatment-related MS activity, and molecular characteristics specific for diffuse glioma in MS patients., Results: MS neither predisposes nor protects from the development of gliomas. Patients with glioblastoma WHO grade 4 without isocitratdehydrogenase (IDH) mutations have a longstanding history of MS, whereas patients diagnosed with IDH-mutant astrocytoma WHO grade 2 receive multiple sclerosis diagnosis mostly at the same time or later. Concurrent MS is associated with a lesser extent of tumor resection and a worse prognosis in IDH-mutant glioma patients (PFS 32 vs. 64 months, p = 0.0206). When assessing tumor-intrinsic differences no distinct subgroup-defining methylation pattern is identified in gliomas of MS patients compared to other glioma samples. However, differential methylation of immune-related genetic loci including human leukocyte antigen locus on 6p21 and interleukin locus on 5q31 is found in MS patients vs. matched non-MS patients. In line, inflammatory disease activity increases in 42% of multiple sclerosis patients after brain tumor radiotherapy suggesting a susceptibility of multiple sclerosis brain tissue to pro-inflammatory stimuli such as ionizing radiation., Conclusions: Concurrent low-grade gliomas should be considered in multiple sclerosis patients with slowly progressive, expansive T2/FLAIR lesions. Our findings of typically reduced extent of resection in MS patients and increased MS activity after radiation may inform future treatment decisions., (© 2023. The Author(s).)

Background: The metabolism of tryptophan to kynurenines (KYN) by indoleamine-2,3-dioxygenase or tryptophan-2,3-dioxygenase is a key pathway of constitutive and adaptive tumor immune resistance. The immunosuppressive effects of KYN in the tumor microenvironment are predominantly mediated by the aryl hydrocarbon receptor (AhR), a cytosolic transcription factor that broadly suppresses immune cell function. Inhibition of AhR thus offers an antitumor therapy opportunity via restoration of immune system functions., Methods: The expression of AhR was evaluated in tissue microarrays of head and neck squamous cell carcinoma (HNSCC), non-small cell lung cancer (NSCLC) and colorectal cancer (CRC). A structure class of inhibitors that block AhR activation by exogenous and endogenous ligands was identified, and further optimized, using a cellular screening cascade. The antagonistic properties of the selected AhR inhibitor candidate BAY 2416964 were determined using transactivation assays. Nuclear translocation, target engagement and the effect of BAY 2416964 on agonist-induced AhR activation were assessed in human and mouse cancer cells. The immunostimulatory properties on gene and cytokine expression were examined in human immune cell subsets. The in vivo efficacy of BAY 2416964 was tested in the syngeneic ovalbumin-expressing B16F10 melanoma model in mice. Coculture of human H1299 NSCLC cells, primary peripheral blood mononuclear cells and fibroblasts mimicking the human stromal-tumor microenvironment was used to assess the effects of AhR inhibition on human immune cells. Furthermore, tumor spheroids cocultured with tumor antigen-specific MART-1 T cells were used to study the antigen-specific cytotoxic T cell responses. The data were analyzed statistically using linear models., Results: AhR expression was observed in tumor cells and tumor-infiltrating immune cells in HNSCC, NSCLC and CRC. BAY 2416964 potently and selectively inhibited AhR activation induced by either exogenous or endogenous AhR ligands. In vitro, BAY 2416964 restored immune cell function in human and mouse cells, and furthermore enhanced antigen-specific cytotoxic T cell responses and killing of tumor spheroids. In vivo, oral application with BAY 2416964 was well tolerated, induced a proinflammatory tumor microenvironment, and demonstrated antitumor efficacy in a syngeneic cancer model in mice., Conclusions: These findings identify AhR inhibition as a novel therapeutic approach to overcome immune resistance in various types of cancers., Competing Interests: Competing interests: CK, NS, LR, UR, BB, DS, FP, MG, HGR, CO, GL, HI, RL, JL, MO-W, RC, HW, IVH, BK and IG are current or former employees of Bayer. NS, UR, BB, MG, GL, HI, RL, JL, FC, DB, CAO, HW, IVH and IG are stockholders of Bayer AG. CK, NS, LR, UR, BB, DS, HI, RC, MP and IG hold patents connected to this work.AS and CAO are founders and managing directors of cAHRmeleon Bioscience GmbH. Some of the authors have patents on AHR inhibitors in cancer (WO2013034685, MP; CAO); A method to multiplex tryptophan and its metabolites (WO2017072368, MP, CAO); A transcriptional signature to determine AHR activity (WO2020201825, AS, CAO); Interleukin-4-induced gene 1 (IL4I1) as a biomarker (WO2020208190, AS,CAO); Interleukin-4-induced gene 1 (IL4I1) and its metabolites as biomarkers for cancer (WO2021116357, AS, CAO).No disclosures were reported by the other authors., (© Author(s) (or their employer(s)) 2023. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)