A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings

Electrical load forecasting plays a vital role in order to achieve the concept of next generation power system such as smart grid, efficient energy management and better power system planning. As a result, high forecast accuracy is required for multiple time horizons that are associated with regulation, dispatching, scheduling and unit commitment of power grid. Artificial Intelligence (AI) based techniques are being developed and deployed worldwide in on Varity of applications, because of its superior capability to handle the complex input and output relationship. This paper provides the comprehensive and systematic literature review of Artificial Intelligence based short term load forecasting techniques. The major objective of this study is to review, identify, evaluate and analyze the performance of Artificial Intelligence (AI) based load forecast models and research gaps. The accuracy of ANN based forecast model is found to be dependent on number of parameters such as forecast model architecture, input combination, activation functions and training algorithm of the network and other exogenous variables affecting on forecast model inputs. Published literature presented in this paper show the potential of AI techniques for effective load forecasting in order to achieve the concept of smart grid and buildings.

A comparison of different study load classifications and their association to student performance: an exploratory study

Purpose – The purpose of this paper is to investigate the alternative study load measures (dichotomous full-time/part-time classification and the number of units enrolled) and their association to student performance by using student data from a final year accounting unit in a large Australian university.

Design/methodology/approach – Using regression analysis, the authors compare the two measures to ascertain the explanatory power of the two approaches in explaining student performance.

Findings – A positive association is found between study loads and student performance when using the “number of units enrolled” measure. This relationship was not found when the dichotomous measure (full-time vs part-time) was used. The results suggest that a scaled measure of study loads is a better measure compared to a binary (dichotomous) measure.

Research limitations/implications – The study will assist future researchers to better control for study loads, and also to gain a better understanding of the association between study loads and student performance. This may possibly assist educational institutions and academics to use a more appropriate pedagogical design in the structure of courses when determining study load allocations across the different cohorts.

Practical implications – This study will help in methodology of future researchers controlling for study loads and student performance.
Originality/value – The study adds to existing literature by providing an alternate study load measure in methodology for controlling for student performance.

Predicting physiological capacity of human load carriage - a review

This review article aims to evaluate a proposed maximum acceptable work duration model for load carriage tasks. It is contended that this concept has particular relevance to physically demanding occupations such as military and firefighting. Personnel in these occupations are often required to perform very physically demanding tasks, over varying time periods, often involving load carriage. Previous research has investigated concepts related to physiological workload limits in occupational settings (e.g. industrial). Evidence suggests however, that existing (unloaded) workload guidelines are not appropriate for load carriage tasks. The utility of this model warrants further work to enable prediction of load carriage durations across a range of functional workloads for physically demanding occupations. If the maximum duration for which personnel can physiologically sustain a load carriage task could be accurately predicted, commanders and supervisors could better plan for and manage tasks to ensure operational imperatives were met whilst minimising health risks for their workers.

Impacts of integration of wind and solar PV in a typical power network

Integration of solar PV and wind in to the distribution network is one of the most promising challenges of the modern power system networks to meet the growing demand of energy. Analysis of the effects of solar and wind intermittencies in the network are vital to maintain the power quality. Keeping this in view, this research paper focuses on impact analysis study of a typical power network with hybrid generation: solar PV and wind integration to quantify the level of impacts like power variation and voltage variation in the network through load flow analysis. Initially, a typical network model is developed using PSS-SINCAL and load profile analysis has been carried out based on the typical daily load profile and wind/solar profile to verify the power and voltage variations extensively in the network considering different scenarios. Results of this research analysis can be used as guidelines for utility grid to provide regulated and improved quality of energy supply by implementing appropriate planning of generation reserve and other control measures in the network

Power quality analysis in microgrid: an experimental approach

Microgrid (MG) integrated with Distributed Generation (DG) provides several benefits like reliable, secure, and high efficient of energy supply, while minimizing power loss, deferring expansion of power distribution infrastructures, and reduced carbon emission of energy supply etc. to the communities. Despite of the several benefits, there are several challenges existing due to the integration of different characteristics and technology of DG sources in MG network. Power Quality (PQ) issue is one of the main technical challenges in MG power system. In order to provide improved PQ of energy supply, it is necessary to analyse and quantify the PQ level in MG network. This paper investigates the detail of PQ impacts in a real MG network carried out through an experimental analysis. Voltage and frequency variations/deviations are analysed in both on-grid and off-grid mode of MG operation at varying generation and varying load conditions. Similarly un-balance voltage and current level in neutral are estimated at unbalanced PV generation and uneven load distribution in MG network. Also current and voltage THD are estimated at different PV power level. Finally the results obtained from the analysis are compared to that of Australian network standard level.

The effect of continuous repetition training and intra-set rest training on bench press strength and power

Lawton et al compare the effects of continuous repetition and intra-set rest training on maximal strength and power output of the upper body. Results show that bench press training involving 4 sets of 6 continuous repetitions elicited a greater improvement in bench press strength than 8 sets of 3 repetitions at the same percentage load of their 6 repetition maximum.

Acoustic and device feature fusion for load recognition

Appliance-specific Load Monitoring (LM) provides a possible solution to the problem of energy conservation which is becoming increasingly challenging, due to growing energy demands within offices and residential spaces. It is essential to perform automatic appliance recognition and monitoring for optimal resource utilization. In this paper, we study the use of non-intrusive LM methods that rely on steady-state appliance signatures for classifying most commonly used office appliances, while demonstrating their limitation in terms of accurately discerning the low-power devices due to overlapping load signatures. We propose a multi-layer decision architecture that makes use of audio features derived from device sounds and fuse it with load signatures acquired from energy meter. For the recognition of device sounds, we perform feature set selection by evaluating the combination of time-domain and FFT-based audio features on the state of the art machine learning algorithms. Further, we demonstrate that our proposed feature set which is a concatenation of device audio feature and load signature significantly improves the device recognition accuracy in comparison to the use of steady-state load signatures only.

Robust control for power sharing in microgrids with low-inertia wind and PV generators

This paper presents a robust control design scheme for a multidistributed energy resource (DER) microgrid for power sharing in both interconnected and islanded modes. The scheme is proposed for micgrogrids consisting of photovoltaic (PV) units and wind turbine driven doubly fed induction generators (DFIGs). A battery is integrated with each of the wind and solar DER units. The control scheme has two levels: 1) one centralized multi-input–multi-output robust controller for regulating the set reference active and reactive powers and 2) local real and reactive power droop con-trollers, one on each DER unit. The robust control scheme utilizes multivariable H1 control to design controllers that are robust to the changes in the network and system nonlinearities. The effectiveness of the proposed controller is demonstrated through large-distur-bance simulations, with complete nonlinear models, on a test micro-grid. It is found that the power sharing controllers provide excellent performance against large disturbances and load variations during islanding transients and interconnected operation.

Distributed generation capacity planning for distribution networks to minimize energy loss: an unbalanced multi-phase optimal power flow based approach

This chapter presents an unbalanced multi-phase optimal power flow (UMOPF) based planning approach to determine the optimum capacities of multiple distributed generation units in a distribution network. An adaptive weight particle swarm optimization algorithm is used to find the global optimum solution. To increase the efficiency of the proposed scheme, a co-simulation platform is developed. Since the proposed method is mainly based on the cost optimization, variations in loads and uncertainties within DG units are also taken into account to perform the analysis. An IEEE 123 node distribution system is used as a test distribution network which is unbalanced and multi-phase in nature, for the validation of the proposed scheme. The superiority of the proposed method is investigated through the comparisons of the results obtained that of a Genetic Algorithm based OPF method. This analysis also shows that the DG capacity planning considering annual load and generation uncertainties outperform the traditional well practised peak-load planning.

An improved stability criterion for time-delay power systems with electric vehicles and high voltage direct current power links

This paper presents an improved stability criterion for load frequency control (LFC) of time-delay power systems including AC/HVDC transmission links and EVs. By employing a novel refined Jensen-based inequality, an improved stability condition is derived in terms of feasible linear matrix inequalities (LMIs) which allow us to compute the maximal upper bounds of time-delay ensuring stability of the LFC scheme equipped with an embedded controller. Cases studies here are implemented for LFC scheme of a two-area power system, which is interconnected by parallel (AC/HVDC) links, with embedded proportional integral (PI) controller for discharged EVs. The relationships between the parameters of PI controller, supplementary control of HVDC links and delay margins of the LFC scheme are also discussed. As a consequence of facts, the results of delay margins can be used as a guideline to tune PI controller and set-up parameters for HVDC control.

H∞ dynamic output feedback control of power systems with electric vehicles

This paper presents a H∞ dynamic output feedback control scheme for load frequency control (LFC) of interconnected power systems with multiple input timedelays. In this study, electric vehicles (EVs) are participated in the LFC to support reheated thermal power units to rapidly suppress load and frequency fluctuations. A mathematical model of an interconnected power system is first introduced. This model takes into consideration of the different time delays in control inputs; specifically the communication/information delays between the control center and the fleet of EVs. We then derive stabilization conditions in terms of feasible linear matrix inequalities (LMIs) for the proposed system and develop an effective algorithm to parameterize H∞ controllers ensuring stability of the closed-loop system with H∞ performance. Extensive simulations are given to show the effectiveness of the proposed control method.

Improving the quality of load forecasts using smart meter data

For the operator of a power system, having an accurate forecast of the day-ahead load is imperative in order to guaranty the reliability of supply and also to minimize generation costs and pollution. Furthermore, in a restructured power system, other parties, like utility companies, large consumers and in some cases even ordinary consumers, can benefit from a higher quality demand forecast. In this paper, the application of smart meter data for producing more accurate load forecasts has been discussed. First an ordinary neural network model is used to generate a forecast for the total load of a number of consumers. The results of this step are used as a benchmark for comparison with the forecast results of a more sophisticated method. In this new method, using wavelet decomposition and a clustering technique called interactive k-means, the consumers are divided into a number of clusters. Then for each cluster an individual neural network is trained. Consequently, by adding the outputs of all of the neural networks, a forecast for the total load is generated. A comparison between the forecast using a single model and the forecast generated by the proposed method, proves that smart meter data can be used to significantly improve the quality of load forecast.

Determining the size of PHEV charging stations powered by commercial grid-integrated PV systems considering reactive power support

Due to low electricity rates at nighttime, home charging for electric vehicles (EVs) is conventionally favored. However, the recent tendency in support of daytime workplace charging that absorbs energy produced by solar photovoltaic (PV) panels appears to be the most promising solution to facilitating higher PV and EV penetration in the power grid. This paper studies optimal sizing of workplace charging stations considering probabilistic reactive power support for plug-in hybrid electric vehicles (PHEVs), which are powered by PV units in medium voltage (MV) commercial networks. In this study, analytical expressions are first presented to estimate the size of charging stations integrated with PV units with an objective of minimizing energy losses. These stations are capable of providing reactive power support to the main grid in addition to charging PHEVs while considering the probability of PV generation. The study is further extended to investigate the impact of time-varying voltage-dependent charging load models on PV penetration. The simulation results obtained on an 18-bus test distribution system show that various charging load models can produce dissimilar levels of PHEV and PV penetration. Particularly, the maximum energy loss and peak load reductions are achieved at 70.17% and 42.95% respectively for the mixed charging load model, where the system accommodates respective PHEV and PV penetration levels of 9.51% and 50%. The results of probabilistic voltage distributions are also thoroughly reported in the paper.

Effects of large dynamic loads on power system stability

This paper investigates the critical parameters of power systems which affect the stability of the system. The analysis is conducted on both a single machine infinite bus (SMIB) system and a large multimachinesystem with dynamic loads. To further investigate the effects of dynamic loads on power system stability, the effectiveness of conventional as well as modern linear controllers is tested and compared with thevariation of loads. The effectiveness is assessed based on the damping of the dominant mode and the analysis in this paper highlights the fact that the dynamic load has substantial effect on the dampingof the system.

Non-intrusive load monitoring approaches for disaggregated energy sensing: a survey.

Appliance Load Monitoring (ALM) is essential for energy management solutions, allowing them to obtain appliance-specific energy consumption statistics that can further be used to devise load scheduling strategies for optimal energy utilization. Fine-grained energy monitoring can be achieved by deploying smart power outlets on every device of interest; however it incurs extra hardware cost and installation complexity. Non-Intrusive Load Monitoring (NILM) is an attractive method for energy disaggregation, as it can discern devices from the aggregated data acquired from a single point of measurement. This paper provides a comprehensive overview of NILM system and its associated methods and techniques used for disaggregated energy sensing. We review the state-of-the art load signatures and disaggregation algorithms used for appliance recognition and highlight challenges and future research directions.