With the emergence of the smart grid (SG), real-time interaction is favorable for both residents and power companies in optimal load scheduling to alleviate electricity cost and peaks in demand. In this paper, a modular framework is introduced for efficient load scheduling. The proposed framework is comprised of four modules: power company module, forecaster module, home energy management controller (HEMC) module, and resident module. The forecaster module receives a demand response (DR), information (real-time pricing scheme (RTPS) and critical peak pricing scheme (CPPS)), and load from the power company module to forecast pricing signals and load. The HEMC module is based on our proposed hybrid gray wolf-modified enhanced differential evolutionary (HGWmEDE) algorithm using the output of the forecaster module to schedule the household load. Each appliance of the resident module receives the schedule from the HEMC module. In a smart home, all the appliances operate according to the schedule to reduce electricity cost and peaks in demand with the affordable waiting time. The simulation results validated that the proposed framework handled the uncertainties in load and supply and provided optimal load scheduling, which facilitates both residents and power companies.

The daily load is the main issue for many power plant industries that are affected by the varying maximum and minimum peak hours. Due to electricity being used less during the weekends, compared to weekdays, where the spending is higher. The same logic applies to day and night spending, which requires balancing among the units so that it can operate during high demand hours. The main problem is to determine the units that will be affected according to the operation schedule which means which unit, and for how long, will it stay on or off. In this context, the main objective for unit commitment, in general, minimizes the total cost of operating a unit, and at the same time maintain the constraints met. Several approaches and techniques used in existing studied, each have a solution for the optimal unit commitment problem. Some of the approaches presented, use complex methods in order to address the issues, while others use simple forms to do the same task. The problem of operation scheduling for unit commitment will be different depending on the type of industry, and according to the plan of mixing unit and operating constraints.

This paper examines the long-term power demand behaviour under the influence of air-conditioning (A/C) systems in Kuwait. An artificial neural network- (ANN-) based simulation model has been developed to forecast the long-term power demand considering different A/C-system quantity import scenarios. Beside the A/C factor, four socio-economic factors are utilized as inputs for the simulation model, including gross national product, population, number of buildings, and historic peak power demand. The baseline scenario shows that the peak power demand will reach 27 440 MW by the year 2025, with an average annual power growth rate of 5.9 per cent. The A/C import quantity scenario shows that an average A/C import quantity change of 1 per cent is proportionate to an ∼1.1 per cent change in power demand.

No abstract

No abstract

Developing a driver monitoring system that can assess the driver’s state is a prerequisite and a key to improving the road safety. With the success of deep learning, such systems can achieve a high accuracy if corresponding high-quality datasets are available. In this paper, we introduce DriverMVT (Driver Monitoring dataset with Videos and Telemetry). The dataset contains information about the driver head pose, heart rate, and driver behaviour inside the cabin like drowsiness and unfastened belt. This dataset can be used to train and evaluate deep learning models to estimate the driver’s health state, mental state, concentration level, and his/her activity in the cabin. Developing such systems that can alert the driver in case of drowsiness or distraction can reduce the number of accidents and increase the safety on the road. The dataset contains 1506 videos for 9 different drivers (7 males and 2 females) with total number of frames equal 5119k and total time over 36 h. In addition, evaluated the dataset with multi-task temporal shift convolutional attention network (MTTS-CAN) algorithm. The algorithm mean average error on our dataset is 16.375 heartbeats per minute.

No abstract

No abstract