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.

Highly-twisted, continuous nanofibre yarns prepared by a hybrid needle-needleless electrospinning technique

Nanofibres prepared by electrospinning have shown enormous potential for various applications. They are obtained predominantly in the form of nonwoven fibre webs. The 2-dimensional nonwoven feature and fragility have considerably confined their further processing into fabrics through knitting or weaving. Nanofibre yarns, which are nanofibre bundles with continuous length and a twist feature, show improved tensile strength, offering opportunities for making 3-dimensional fibrous materials with precisely controlled fibrous architecture, porous features and fabric dimensions. Despite a few techniques having been developed for electrospinning nanofibre yarns, they are chiefly based on the needle electrospinning technique, which often has low nanofibre productivity. In this study, we for the first time report a nanofibre yarn electrospinning technique which combines both needle and needleless electrospinning. A rotating intermediate ring collector was employed to directly collect freshly-electrospun nanofibres into a fibrous cone, which was further drawn and twisted into a nanofibre yarn. This novel system was able to produce high tenacity yarn (tensile strength 128.9 MPa and max strain 222.1%) at a production rate of 240 m h^-1, with a twist level up to 4700 twists per metre. The effects of various parameters, e.g. position of the electrospinning units, operating conditions and polymer concentration, on nanofibre and yarn production were examined.