Short term load forecasting using a hybrid neural network

Short Term Load Forecasting (STLF) is very important from the power systems grid operation point of view. STLF involves forecasting load demand in a short term time frame. The short term time frame may consist of half hourly prediction up to weekly prediction. Accurate forecasting would benefit the utility in terms of reliability and stability of the grid ensuring adequate supply is present to meet with the load demand. Apart from that it would also affect the financial performance of the utility company. An accurate forecast would result in better savings while maintaining the security of the grid. This paper outlines the STLF using a novel hybrid online learning neural network, known as the Gaussian Regression (GR). This new hybrid neural network is a combination of two existing online learning neural networks which are the Gaussian Adaptive Resonance Theory (GA) and the Generalized Regression Neural Network (GRNN). Both GA and GRNN implemented online learning, but each of them suffers from limitation. Originally GA is used for unsupervised clustering by compressing the training samples into several categories. A supervised version of GA is available, namely Gaussian ARTMAP (GAM). However, the GAM is still not capable on solving regression problem. On the other hand, GRNN is designed for solving real value estimation (regression) problem, but the learning process would involve of memorizing all training samples, hence high computational cost. The hybrid GR is considered an enhanced version of GRNN with compression ability while still maintains online learning properties. Simulation results show that GR has comparable prediction accuracy and has less prototype as compared to the original GRNN as well as the Support Vector Regression.

Corticospinal excitability following short-term motor imagery training of a strength task

Motor imagery and actual movement engage similar neural structures, however, whether they produce similar training-related corticospinal adaptations has yet to be established. The aim of this study was to compare changes in strength and corticospinal excitability following short-term motor imagery strength training and short-term strength training. Transcranial magnetic stimulation (TMS) was applied over the contralateral motor cortex (M1) to elicit motor-evoked potentials in the dominant biceps brachii muscle prior to and following 3-week strength training using actual bicep curls or motor imagery of bicep curls. The strength training (n = 6) and motor imagery (n = 6) groups underwent three supervised training sessions per week for 3 weeks. Participants completed four sets of six to eight repetitions (actual or imagined) at a training load of 80% of their one-repetition maximum. The control group (n = 6) were required to maintain their current level of physical activity. Both training groups exhibited large performance gains in strength (p < 0.001; strength training 39% improvement, imagery 16% improvement), which were significantly different between groups (p = 0.027). TMS revealed that the performance improvements observed in both imagery and strength training were accompanied by increases in corticospinal excitability (p < 0.001), however, these differences were not significantly different between groups (p = 0.920). Our findings suggest that both strength training and motor imagery training utilised similar neural substrates within the primary M1, however, strength training resulted in greater gains in strength than motor imagery strength training. This difference in strength increases may be attributed to adaptations during strength training that are not confined to the primary M1. These findings have theoretical implications for functional equivalent views of motor imagery as well as important therapeutic implications.

Prediction intervals for short-term wind farm power generation forecasts

Quantification of uncertainties associated with wind power generation forecasts is essential for optimal management of wind farms and their successful integration into power systems. This paper investigates two neural network-based methods for direct and rapid construction of prediction intervals (PIs) for short-term forecasting of power generation in wind farms. The lower upper bound estimation and bootstrap methods are used to quantify uncertainties associated with forecasts. The effectiveness and efficiency of these two general methods for uncertainty quantification is examined using twenty four month data from a wind farm in Australia. PIs with a confidence level of 90% are constructed for four forecasting horizons: five, ten, fifteen, and thirty minutes. Quantitative measures are applied for objective evaluation and unbiased comparison of PI quality. Demonstrated results indicate that reliable PIs can be constructed in a short time without resorting to complicate computational methods or models. Also quantitative comparison reveals that bootstrap PIs are more suitable for short prediction horizon, and lower upper bound estimation PIs are more appropriate for longer forecasting horizons.

Regulation of miRNAs in human skeletal muscle following acute endurance exercise and short-term endurance training

The identification of microRNAs (miRNAs) has established new mechanisms that control skeletal muscle adaptation to exercise. The present study investigated the mRNA regulation of components of the miRNA biogenesis pathway (Drosha, Dicer and Exportin-5), muscle enriched miRNAs, (miR-1, -133a, -133b and -206), and several miRNAs dysregulated in muscle myopathies (miR-9, -23, -29, -31 and -181). Measurements were made in muscle biopsies from nine healthy untrained males at rest, 3 h following an acute bout of moderate-intensity endurance cycling and following 10 days of endurance training. Bioinformatics analysis was used to predict potential miRNA targets. In the 3 h period following the acute exercise bout, Drosha, Dicer and Exportin-5, as well as miR-1, -133a, -133-b and -181a were all increased. In contrast miR-9, -23a, -23b and -31 were decreased. Short-term training increased miR-1 and -29b, while miR-31 remained decreased. Negative correlations were observed between miR-9 and HDAC4 protein (r=-0.71; P= 0.04), miR-31 and HDAC4 protein (r =-0.87; P= 0.026) and miR-31 and NRF1 protein (r =-0.77; P= 0.01) 3 h following exercise. miR-31 binding to the HDAC4 and NRF1 3′ untranslated region (UTR) reduced luciferase reporter activity. Exercise rapidly and transiently regulates several miRNA species in muscle. Several of these miRNAs may be involved in the regulation of skeletal muscle regeneration, gene transcription and mitochondrial biogenesis. Identifying endurance exercise-mediated stress signals regulating skeletal muscle miRNAs, as well as validating their targets and regulatory pathways post exercise, will advance our understanding of their potential role/s in human health

Short-term intensified cycle training alters acute and chronic responses of PGC1α and cytochrome C oxidase IV to exercise in human skeletal muscle

Reduced activation of exercise responsive signalling pathways have been reported in response to acute exercise after training; however little is known about the adaptive responses of the mitochondria. Accordingly, we investigated changes in mitochondrial gene expression and protein abundance in response to the same acute exercise before and after 10-d of intensive cycle training.

Nine untrained, healthy participants (mean±SD; VO2peak 44.1±17.6 ml/kg/min) performed a 60 min bout of cycling exercise at 164±18 W (72% of pre-training VO2peak). Muscle biopsies were obtained from the vastus lateralis muscle at rest, immediately and 3 h after exercise. The participants then underwent 10-d of cycle training which included four high-intensity interval training sessions (6×5 min; 90–100% VO2peak) and six prolonged moderate-intensity sessions (45–90 min; 75% VO2peak). Participants repeated the pre-training exercise trial at the same absolute work load (64% of pre-training VO2peak). Muscle PGC1-α mRNA expression was attenuated as it increased by 11- and 4- fold (P<0.001) after exercise pre- and post-training, respectively. PGC1-α protein expression increased 1.5 fold (P<0.05) in response to exercise pre-training with no further increases after the post-training exercise bout. RIP140 protein abundance was responsive to acute exercise only (P<0.01). COXIV mRNA (1.6 fold; P<0.01) and COXIV protein expression (1.5 fold; P<0.05) were increased by training but COXIV protein expression was decreased (20%; P<0.01) by acute exercise pre- and post-training.

These findings demonstrate that short-term intensified training promotes increased mitochondrial gene expression and protein abundance. Furthermore, acute indicators of exercise-induced mitochondrial adaptation appear to be blunted in response to exercise at the same absolute intensity following short-term training.

Short term aerobic exercise training in young males does not alter sensitivity to a central serotonin agonist

An increase in the concentration of serotonin in the brain has been shown to cause fatigue during exercise in humans and experimental animals. This type of fatigue is referred to as central fatigue and is likely to be mediated by the concentration of serotonin as well as serotonin receptor sensitivity. Serotonin (5-HT) receptor antagonism in humans and experimental animals has been shown to improve endurance performance. A previous report has shown decreased receptor sensitivity in athletes compared to sedentary controls. It is unclear whether this is due to a training adaptation or if individuals are predisposed to enhanced athletic performance due to their inherent decreased receptor sensitivity. The present study investigated changes in 5-HT receptor sensitivity in response to aerobic exercise. Subjects completed 3 × 30 min of stationary cycling at 70% of their peak aerobic power (V̇O2,peak) for 9 weeks. Serotonin receptor sensitivity was assessed indirectly by measuring the neuroendocrine response following administration of a serotonin agonist (buspirone hydrochloride). The neuroendocrine response following administration of a placebo was also investigated in a blind crossover design. A group of sedentary control subjects was also recruited to control for seasonal variations in central receptor sensitivity. The training caused a significant increase in V̇O2,peak (3.1 ± 0.16 to 3.6 ± 0.15 l min−1, P < 0.05) and endurance capacity (93 ± 8 to 168 ± 11 min, P < 0.05), but there was no change (P > 0.05) in the neuroendocrine response in the presence of a serotonin agonist. However, one-quarter of the subjects in the training group demonstrated decreases in receptor sensitivity. These results suggest that despite increases in V̇O2,peak and endurance performance, there was no measurable change in 5-HT receptor sensitivity in the presence of a serotonin agonist. In addition, it is possible that changes in receptor sensitivity may take longer to occur, that the training stimulus used in the present investigation was inadequate and/or that changes occurred in receptor subtypes that were not probed by the agonist used in the present investigation.

Reducing sitting time in office workers: short-term efficacy of a multicomponent intervention

Objective To investigate the short-term efficacy of a multicomponent intervention to reduce office workers' sitting time. Methods Allocation for this non-randomized controlled trial (n = 43 participants; 56% women; 26–62 years; Melbourne, Australia) was by office floor, with data collected during July–September 2011. The 4-week intervention emphasized three key messages: “Stand Up, Sit Less, Move More” and comprised organizational, environmental, and individual elements. Changes in minutes/day at the workplace spent sitting (primary outcome), in prolonged sitting (sitting time accumulated in bouts ≥ 30 min), standing, and moving were objectively measured (activPAL3). Results Relative to the controls, the intervention group significantly reduced workplace sitting time (mean change [95%CI]: − 125 [− 161, − 89] min/8-h workday), with changes primarily driven by a reduction in prolonged sitting time (− 73 [− 108, − 40] min/8-h workday). Workplace sitting was almost exclusively replaced by standing (+ 127 [+ 92, + 162] min/8-h workday) with non-significant changes to stepping time (− 2 [− 7, + 4] min/8-h workday) and number of steps (− 70 [− 350, 210]). Conclusions This multicomponent workplace intervention demonstrated that substantial reductions in sitting time are achievable in an office setting. Larger studies with longer timeframes are needed to assess sustainability of these changes, as well as their potential longer-term impacts on health and work-related outcomes.

Short-term load and wind power forecasting using neural network-based prediction intervals

Electrical power systems are evolving from today's centralized bulk systems to more decentralized systems. Penetrations of renewable energies, such as wind and solar power, significantly increase the level of uncertainty in power systems. Accurate load forecasting becomes more complex, yet more important for management of power systems. Traditional methods for generating point forecasts of load demands cannot properly handle uncertainties in system operations. To quantify potential uncertainties associated with forecasts, this paper implements a neural network (NN)-based method for the construction of prediction intervals (PIs). A newly introduced method, called lower upper bound estimation (LUBE), is applied and extended to develop PIs using NN models. A new problem formulation is proposed, which translates the primary multiobjective problem into a constrained single-objective problem. Compared with the cost function, this new formulation is closer to the primary problem and has fewer parameters. Particle swarm optimization (PSO) integrated with the mutation operator is used to solve the problem. Electrical demands from Singapore and New South Wales (Australia), as well as wind power generation from Capital Wind Farm, are used to validate the PSO-based LUBE method. Comparative results show that the proposed method can construct higher quality PIs for load and wind power generation forecasts in a short time.

Construction of neural network-based prediction intervals for short-term electrical load forecasting

Short-term load forecasting (STLF) is of great importance for control and scheduling of electrical power systems. The uncertainty of power systems increases due to the random nature of climate and the penetration of the renewable energies such as wind and solar power. Traditional methods for generating point forecasts of load demands cannot properly handle uncertainties in datasets. To quantify these potential uncertainties associated with forecasts, this paper implements a neural network (NN)-based method for construction of prediction intervals (PIs). A newly proposed method, called lower upper bound estimation (LUBE), is applied to develop PIs using NN models. The primary multi-objective problem is firstly transformed into a constrained single-objective problem. This new problem formulation is closer to the original problem and has fewer parameters than the cost function. Particle swarm optimization (PSO) integrated with the mutation operator is used to solve the problem. Two case studies from Singapore and New South Wales (Australia) historical load datasets are used to validate the PSO-based LUBE method. Demonstrated results show that the proposed method can construct high quality PIs for load forecasting applications.

Short-term impacts of the cricket match performances on national share markets – a case study of India and Australia

We investigate the impact that investor sentiment can have on stock market following performances by the national cricket teams of India and Australia in one-day cricket matches from 1990 to 2011. Motivated by previous findings of cricket’s impacts on stock markets, this study expands on previous research by investigating whether performances of individuals within the teams can also have an impact on their respective leading stock indices. Using an event study, we find no evidence of player or team performances significantly impacting the stock or futures markets. However, we find evidence of a ‘mood effect’ of poor performance by key players of national cricket teams in terms of significant drop in trading volumes in the following day. Our research poses and statistically examines some interesting questions and opens up the field for further research on this intriguing topic of sporting event impacts on national economies.