Heiko Hahn

Bio: Heiko Hahn is an academic researcher from Bundeswehr University Munich. The author has contributed to research in topics: Emissions trading & Decision support system. The author has an hindex of 3, co-authored 3 publications receiving 461 citations.

The impact of uncertain emission trading markets on interactive resource planning processes and international emission trading experiments

Abstract: Interactive resource planning is an increasingly important aspect of emission trading markets. The conferences of Rio de Janeiro, 1992, and Kyoto, 1997, originally focusing on environmental protection at both macro- and micro-economic levels, called for new economic instruments of this kind. An important economic tool in this area is Joint Implementation (JI), defined in Article 6 of the Kyoto Protocol. Sustainable development can be guaranteed only if JI is embedded in optimal energy management. In this contribution we describe and evaluate one international procedure within uncertain markets which helps to establish optimal energy management and interactive resource planning processes within uncertain emission trading markets.

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

Abstract: 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.

Big data driven smart energy management: From big data to big insights

Abstract: Large amounts of data are increasingly accumulated in the energy sector with the continuous application of sensors, wireless transmission, network communication, and cloud computing technologies. To fulfill the potential of energy big data and obtain insights to achieve smart energy management, we present a comprehensive study of big data driven smart energy management. We first discuss the sources and characteristics of energy big data. Also, a process model of big data driven smart energy management is proposed. Then taking smart grid as the research background, we provide a systematic review of big data analytics for smart energy management. It is discussed from four major aspects, namely power generation side management, microgrid and renewable energy management, asset management and collaborative operation, as well as demand side management (DSM). Afterwards, the industrial development of big data-driven smart energy management is analyzed and discussed. Finally, we point out the challenges of big data-driven smart energy management in IT infrastructure, data collection and governance, data integration and sharing, processing and analysis, security and privacy, and professionals.

A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines

Abstract: This paper presents a generic strategy for short-term load forecasting (STLF) based on the support vector regression machines (SVR). Two important improvements to the SVR based load forecasting method are introduced, i.e., procedure for generation of model inputs and subsequent model input selection using feature selection algorithms. One of the objectives of the proposed strategy is to reduce the operator interaction in the model-building procedure. The proposed use of feature selection algorithms for automatic model input selection and the use of the particle swarm global optimization based technique for the optimization of SVR hyper-parameters reduces the operator interaction. To confirm the effectiveness of the proposed modeling strategy, the model has been trained and tested on two publicly available and well-known load forecasting data sets and compared to the state-of-the-art STLF algorithms yielding improved accuracy.