Search

This paper addresses the problem of efficiently operating a flexible manufacturing machine in an electricity micro-grid featuring a high volatility of electricity prices. The problem of finding the optimal control policy is formulated as a sequential decision making problem under uncertainty where, at every time step the uncertainty comes from the lack of knowledge about fu-ture electricity consumption and future weather dependent energy prices. We propose to address this problem using deep reinforcement learning. To this purpose, we designed a deep learning architecture to forecast the load profile of future manufacturing schedule from past production time series. Combined with the forecast of future energy prices, the reinforcement-learning algorithm is trained to perform an online optimization of the production ma-chine in order to reduce the long-term energy costs. The concept is empirical-ly validated on a flexible production machine, where the machine speed can be optimized during the production.

In the field of energy supply for residential and commercial buildings, the optimal operation,system configuration and sizing of generation as well as storage technologies are essential stepsfor cost-efficient investments. In current research, flexibility options for electricity from growing renewableenergies attract attention. One of the considered options is the power-to-gas technology incombination with fuel cells. Linear Programs for optimal system operation exist for example for distributedenergy systems. In this study we propose a Mixed Integer Linear Program of a power-to-gasunit consisting of an electrolyzer, a fuel cell and a hydrogen storage. For the fuel cell a minimum loadand a non-linear efficiency curve is taken into account. The non-linear efficiency curve is approximatedby piecewise linearization. Bilinear products in the modeling of the efficiency curve are beingsubstituted to maintain full power plant sizing and operation functionality. Different fuels, such as naturalgas and hydrogen to be converted in the fuel cell, are implemented as well. As a result, we showthat a detailed model of the non-linear efficiency curve of a fuel cell leads to more accurate results concerningthe system operation. The configuration of system components in the observed energy systemchanges. Especially the battery system experiences a change in sizing and operation. However, solvingtime of the model is increasing dramatically. Our results demonstrate a valuable approach to comparethe results of a Linear Program to a Mixed Integer Linear Program. Hence giving the possibility toevaluate the necessity of detailed over simplified models regarding calculation of cost-effectiveness.

In contrast to conventional hydronic heating systems, in which the air is used as a medium for the convective heat transfer, an alternative approach is based on the usage of infrared (IR) radiant heating foils. These foils, which are applied to the walls and the ceiling of a laboratory, can be controlled individually. This leads to the possibility of heating the room zonewise and only when a person is present in a zone. A local comfortable climate is provided only in occupied zones, with the remaining zones being kept at a lower base temperature. Consequently, the measurement system has to detect persons in each zone and to determine the putative thermal comfort at relevant locations in the room. For the first problem, we examined and evaluated different sensor types capable of localizing persons without infringing on their anonymity. For the second problem, we used the fact that the thermal comfort mainly depends on the operative temperature (Li et al., 2010; DIN EN ISO 7730, 2006; de Dear and Brager, 2002). According to Simone et al. (2007), this temperature can be measured directly by an easily producible, planar sensor. The sensors were integrated in a wireless sensor network which consists of Wi-Fi-capable microcontroller boards, wireless smart home equipment, a Wi-Fi router, and a server.

The central heating units of buildings are typically replaced every 20 to 30 years. There exists a variety of solutions for fuel-and gas-based units, but it would be advantageous to be able to use renewable energies. This would become possible by the combination of planar carbon-fiber-based infrared (IR) radiant heating foils with a heat pump providing hot water. The main goal of our proposed overall control strategy is to increase the energy efficiency while maintaining the thermal comfort for the residents. We examined the electromagnetic compatibility of the heating foils and simulated the relative contributions of the amount of energy provided by the heat pump and by the heating foils to obtain a maximum coefficient of performance for the combined heating system.

The transition from fossil generated energy towards regenerative energy sources is an important topic. Especially the generation from wind power plants and photovoltaic systems underlines the most important difference in comparison to conventional energy generation and distribution. One of the main characteristics of renewable energy sources is its decentralized generation, where existing distribution paths will become more and more a bottleneck in the future. The solution for this challenge is called smart grid and is driven by information, such as energy consumption, in order to match energy demand and supply. The SmartEco idea makes it possible to offload some of the energy’s surplus form the grid to individual customer homes in the context of the smart gird approach.

In electric energy systems based on renewable generation plants supply and demand often do not occur in the same period of time. Consequently demand side management is gaining importance whereby decentralized automation offers opportunities in industrial environments. Compressed air systems on industrial plants consist of air compressors, compressed air reservoirs and compressed air lines. With suitable dimensioning those industrial compressed-air systems can be used for demand side management purpose. As power consumption of industrial air compressors ranges between a few and several hundred kilowatts each, swarms of communicatively connected air compressors can contribute to the stabilization of power grids. To avoid costly production downtime it is to ensure, that a reliable, non-disruptive supply of compressed air can be maintained at all time. Industrial compressed air systems equipped with automation technology and artificial intelligence, which hereinafter are referred to as Cyber-Physical Compressed Air Systems (CPCAS), allow new business models for utilities, industrial enterprises, compressor manufacturers and service providers. In addition to basic operating parameters like current air pressure and status, those systems can process further information and create, for example, profiles on compressed air consumption over time. By enriching those profiles with data on pressure, volumes, system restrictions and current production requirements (plans), the CPCAS can identify the available potential for demand side management. Ipso facto predictive power on electricity consumption is increasing. By providing the information obtained to the power company or a service provider, savings in electricity costs may be achieved. Expenses within the industrial company may be lowered further as compliance with agreed load limits is being improved by automatic shutdown of air compressors upon reaching the load limit. Within this article the structure of the aforementioned Cyber-Physical Compressed Air Systems is presented in more detail, relations between the major actors are being shown and possible business models are being introduced.

This chapter presents novel approaches for the efficient generation, storage, and usage of energy in the smart home environment and their link to the smart grid. It also demonstrates innovative concepts and their feasibility for these purposes. The generation of renewable energy on the level of individual homes and housing estates is achieved by aerodynamically and aeroacoustically optimized small wind turbines as well as combined heat and power (CHP) micro plants using organic Rankine cycles (ORCs) to complement solar energy. The chapter further discusses the intelligent distribution of electric energy between the smart home and the smart grid. In order to tackle the transition of the electric power supply toward a renewable‐based generation plant system, it is necessary to fully exploit locally available energy sources and to generate production surpluses in rural areas for the supply of urban agglomerations and industrial centers.

Since storage technologies are very expensive in acquisition, possibilities of demand side management (DSM) are of increasing interest. In this paper the results of a potential analysis for DSM applications within the field of domestic living is presented. This analysis shows the high DSM-potential for electric storage heaters in Germany. So, a system approach for the interconnection of individual electric storage heaters with the control center of the energy supply company is developed thus creating a bidirectional communication between households and the energy supply company. This system architecture makes it possible, especially for small and local energy suppliers, to offload some of the energy surplus from the grid into individual customer homes.

The aim of this study is to develop a new kind of heating system that eliminates existing disadvantages and expands current advantages. This includes the poor efficiency of gas and oil heaters, the high installation effort for connecting the central heating as well as low heat-transfer rates. Investigations point out that warm ambient surfaces increase the physical living comfort without heating up the air inside rooms while reducing costs. These conditions can be achieved by radiation heating where heat is not stored in the air and thus not lost in case of ventilation. In this paper, a new approach will be described, where radiation heating is applied to a variety of surfaces of domestic objects by a new technology. This technology offers new opportunities in contrast to commercial systems of radiation heating, which are largely applied on planar walls. Furthermore, it will be outlined how this technology can be used for radiation heating on desks, so anyone can adjust its own feel-good temperature in the office. A concept that allows providing heat exactly where it is required, e.g. in the proximity of a person, is developed.

The transition from conventionally generated energy towards renewable energy sources is an important topic. Besides the need for new concepts for power plants this paradigm shift also implies new structural requirements for the grid. Especially, the on premise generation of energy via photovoltaics underlines the most important difference as compared to conventional energy generation and distribution. The structure of the grid, for most parts, still follows the pattern of a strong root connection from the power plant, transforming the energy for lower power distribution branches multiple times on the way to the consumer. One of the main characteristics of renewable energy sources is its more consumer local and distributed generation, where existing distribution paths will become more and more of a bottleneck in the future. One way to solve this problem would be to relinquish the current grid structure and replace it with a new more suitable one. Yet, such a fundamental structural change would require a very long time to be installed and induce cost far beyond benefit. The current solution, commonly called smart grid, is mostly driven by information, such as energy consumption amounts and times of customers, in order to match energy generation, distribution and consumption. Our SmartEco approach goes one step further and makes it possible, especially for small and local energy suppliers, to even offload some of the energy surplus from the grid into individual customer homes.