Analytics for Smart Energy Management

The goal of this chapter is to introduce subjects and methods covered in this book and give an overview of the remaining chapters. It first gives the background of sustainable manufacturing and reviews energy consumption in US automotive industry. Then, it discusses the energy and environment management in the automotive industry. It also discusses the idea of using data and model-based analytics for smart energy and environment management. To provide a flavour of approaches used in this book, a cost comparison of pneumatic and electric actuator systems is illustrated as an example decision problem in energy management. Compressed air is frequently used in manufacturing plants to power pneumatic actuators, which are used for many applications including clamping, loading and spray-painting. On average, compressed air accounts for more than 10 % of total energy costs in a manufacturing plant. Unfortunately, it is highly inefficient because as much as 50 % of compressed air can be lost through leaks or excess pressurization in the distribution system. Given these flaws of compressed air, it becomes an important decision problem to compare the cost of pneumatic and electric actuators (as an alternative to pneumatic actuators) and find the right solution. Lastly, this chapter provides summaries of the contents of the remaining chapters in this book.

Energy performance analysis in the car manufacturing industry is intriguing. The car manufacturing industry, one of the largest energy consuming industries, has been making a considerable effort to improve its energy intensity by implementing energy efficiency programs, in many cases supported by government research or financial programs. While many car manufacturers claim that they have made substantial progress in energy efficiency improvement over the past years through their energy efficiency programs, the objective measurement of energy efficiency improvement has not been studied due to the lack of suitable quantitative methods. This chapter proposes stochastic and deterministic frontier benchmarking models such as the stochastic frontier analysis (SFA) model and the data envelopment analysis (DEA) model to measure the effectiveness of energy saving initiatives in terms of the technical improvement of energy efficiency for the automotive industry, particularly vehicle assembly plants. Illustrative examples of the application of the proposed models are presented and demonstrate the overall benchmarking process to determine best practice frontier lines and to measure technical improvement based on the magnitude of frontier line shifts over time. Log likelihood ratio and Spearman rank-order correlation coefficient tests are conducted to determine the significance of the SFA model and its consistency with the DEA model. ENERGY STAR^® EPI (Energy Performance Index) are also calculated. This chapter also provides a short instruction to Excel Solver by illustrating three examples: (1) SFA parameters estimation (2) DEA LP problem and (3) traveling compressed air expert problem, with an attempt to help readers learn and use GRG method, Simplex LP method and evolutionary method, respectively.

The need of energy decision making happens in realizing sustainable manufacturing. Many companies in the manufacturing industry have realized the importance of sustainability and have made a strategic move toward sustainable manufacturing to face the uncertainty of future energy availability and stringent environment regulations enacted around the world. However, it is a challenge to build a strategic plan for implementing sustainable manufacturing projects in such a way as to optimize energy efficiency opportunities while remaining in compliance with environmental regulations especially when future uncertainties, such as a fluctuation in energy prices or CO₂ credit costs, are involved. This chapter proposes a new stochastic programming approach to identify the optimal investment plan for sustainable manufacturing projects to reduce energy and CO₂ emission costs for manufacturing processes subject to various time, budget, technology and environmental constraints. The principle underlying the proposed approach is to solve a multi-period stochastic programming involving uncertain decision parameters, such as future CO₂ credit market price, through the use of sample averaging approximation (SAA). An illustrative example application of the proposed model to an automotive company is presented. In Appendix, this chapter also provides an overview of the available standards and methods that can be used for preparing Scope 3 green house gas inventories and carbon footprints for organizations and their specific products or services.

The need of energy decision making happens in smart grids. Smart grids enable a two-way energy demand response capability through which a utility company offers its industrial customers various call options for energy load curtailment. If a customer has the capability to accurately determine whether to accept an offer or not, then in the case of accepting an offer, the customer can earn both an option premium to participate, and a strike price for load curtailments if requested. However, today most manufacturing companies lack the capability to make the correct contract decisions for given offers. This chapter introduces a novel decision model based on activity-based costing (ABC) and stochastic programming, developed to accurately evaluate the impact of load curtailments and determine as to whether or not to accept an energy load curtailment offer. The introduced model specifically targets state-transition flexible and Quality-of-Service (QoS) flexible energy use activities to reduce the peak energy demand rate. An illustrative example with the proposed decision model under a call-option based energy demand response scenario is presented. As shown from the example results, the proposed decision model can be used with emerging smart grid opportunities to provide a competitive advantage to the manufacturing industry.

It is often required to carry out sensor-based condition monitoring for machines or operations (e.g., machining centre, foundry) during production to ensure the effectiveness. Due to the requirements of a non-invasive installation or no interruption during production, however, it may be difficult to fully instrument the machine or production equipment with monitoring sensors. As an alternative to the direct monitoring, it is possible to use energy power or temperature data, and other easy-to-install sensors measured with relatively high time resolution (~2 s) to provide enough information to effectively infer events and other properties. From this reason, the ability of inferring becomes important. To introduce how the inferencing technology can be used in the energy management, this chapter presents a pattern-based energy consumption analysis by chaining Principle Component Analysis (PCA) and logistic regression. The PCA provides an unsupervised dimension reduction to mitigate the issue of multicollinearity (high dependence) among the explanatory variables, while the logistic regression does the prediction based on the reduced dataset expressed in orthogonal axes that are uncorrelated principle components represented by Eigenvectors found in the PCA. By chaining the PCA and logistic regression, it is possible to train manually time-logged energy data and to infer the events associated with the manufacturing operations. It is expected that the proposed analysis method will enable manufacturing companies to correlate energy and operations and further use the power data to predict when operation events of interest (e.g. start up, idle, peak operation, etc.) occur, resulting in determining how current energy usage levels in manufacturing operations compares to the optimal usage patterns. This chapter also provides a short instruction to Python and IPython Notebook. It illustrates a supervised learning process by using Python to carry out pipelining PCA and logistic regression and applying a grid search to training and inference energy consumption patterns.

It is critical for global manufacturing enterprises to know and understand regional and local environmental regulations and incentive programs/polices. However, there has been little research aimed at acquiring and disseminating the knowledge of environmental regulations and incentive policies within the business decision making context, especially for the manufacturing industry sector. To address this problem, this chapter presents the Environmental Regulation and Incentive Policies Acquisition and Dissemination (ERIPAD) ontology. This ontology can enable systematic knowledge acquisition and personalized knowledge dissemination via reasoning query languages like SPARQL with its query engine, Apache Jena Fuseki. The ERIPAD ontology is currently customized for the European Union Emission Trading Scheme and the Waxman-Markey bill because of their comprehensiveness and inclusiveness. It is expected that the ERIPAD ontology will enable manufacturing companies to improve agility and efficiency in their energy or environment related decision making process.

Recently, the importance of balancing building and process energy in manufacturing is growing because both comfortable working environment and energy efficiency have emerged as important element for advancing the manufacturing system. One way of achieving the balance is to optimize the operation of HVAC system (Heating, Ventilating and Air Conditioning System) in such a way that temperatures and states of heating and cooling are optimized. In this chapter, plant energy simulation models are developed by customizing EnergyPlus™ (below written as EnergyPlus) and two new HVAC control approaches such as air conditioning economizer and dynamic mist control are evaluated with the developed energy models. The simulation results reveal that (1) the use of air conditioning economizer can save 8.4 % yearly cooling energy compared to the business-as-usual case without compromising the working quality for a selected example location; (2) the application of dynamic mist control system can save significant cooling and heating energy for machining plants in three selected example locations, at the same time, keeping worker health protection foremost. This chapter also provides a short instruction to EnergyPlus. EnergyPlus was originally developed as a public domain software package to estimate energy consumptions of a building complex. Therefore, its applications are limited to commercial buildings, not industrial facilities. In order to use it for manufacturing facilities, its expansion is required. With an example of a room with welding equipment, the instruction provides step by step guidance toward understanding the details of manufacturing process simulation.

Energy use is a large, but mandatory, expense incurred by manufacturers or facility operators and contributes to Greenhouse Gas (GHG) emissions. Depending on the type of business, energy cost can range from less than 1 % of operating expense to more than 30 %. Additionally, energy use in facilities and operations accounts for 66 % of the total greenhouse gas emissions, with transportation being the remaining 34 % of GHG emissions. Although the expense may be a small portion of operating expense, the cost and environmental impact is significant for many companies. As an example, at General Motors (GM), although the expenditure for energy is less than 1 % of total expenses, the cost is in excess of $1 Billion USD annually. Regardless of any view on climate change, with buildings and facilities being the majority of carbon emissions and the recent reduction emphasis at the United Nations framework convention on climate change, “COP-21” creating international attention from investors and customers, managing GHG emissions has become an important part of business. Hence, a robust Energy Management process is needed to meet the fiscal and environmental responsibility of businesses to remain sustainable and satisfy investors’ and customers’ demands. Management of energy and carbon to reduce environmental impact is important enough to be included in the company’s business plan, similar to safety, people, quality, and cost. Following a model similar to EPA Energy Star’s seven step approach, based on Plan, Do, Check, Act methodology (PDCA), energy management can be integrated into a company’s standard business plan. This requires top level commitment, resources, business planning, goals, and recognition to manage energy and GHG reductions. The methods used to integrate energy management into the business plan include dedicated resources at all levels in the organization. With people as one of most important resources, having qualified energy leaders at the corporate, global, regional and site levels is key to success. To implement initiatives a dedicated budget for systems and projects is required, similar to other areas of the business. Forecasting energy, establishing targets, implementing projects and processes, regular monitoring, and corrective action when required ensures timely adherence to meeting energy and carbon goals. Recognition can be internal with various processes—Plant energy performance recognition, employee suggestions, employee compensation tied to business results, and others, as well as external. The U.S. Environmental Protection Agency (EPA) Energy Star^® certifies plants and facilities similar to laptops and refrigerators. Additionally, Energy Star’s^® Challenge for Industry provides recognition for plants reducing energy intensity by 10 % within five years. The Energy Star^®, also sponsored by the Department of Energy (DOE) Partner of the year award in Energy Management, is EPA’s highest award for exemplary performance.

An important method to reduce Greenhouse gas and energy is through energy efficiency projects. To gain top-level support and funding, a systematic approach is best using data and benchmarking other companies. Explaining why support and funding is required is the first step toward selling the need. To compete with other internal funding needs—product programs, asset sustainment, and maintenance…, a strategic approach is required utilizing company’s standard business practices for energy savings projects. A long-term plan including energy use forecasting, business as usual, the gap to meet the company’s goals, and the spending and savings for multiple years demonstrates a strategic plan to meet the objective. Based on the available funds, prioritize projects based on return on investment, CO₂e reduction, and probability of success. Tracking each project throughout the planning and implementation process demonstrates accountability. Additionally, having a list of shovel ready projects and the status of each can provide an opportunity to gain more funding if it becomes available. Reducing next year’s operating budget by the savings is a good method to sustain the funding year over year. Standardized measure and verification methods provide confirmation to customers and management that energy efficiency efforts really reduce the bottom-line cost and provide an attractive return on investment.