MAISY AI Agent-Based Energy and Hourly Load Forecasting and Analysis Models
MAISY AI Agent-Based End-Use Forecasting Models Address Three Related Issues
MAISY Forecasting Models BackgroundJackson Associates (JA) provides energy and hourly load forecasting models and forecasting services for a variety of clients including electricic utilities, state and federal agencies, technology companies and other energy industry organizations.Our modeling methodologies have advanced from econometric models to aggregate end-use models to state-of-the art agent based end-use models that provide more accurate and more granular modeling including incorporation of specific building and appliance efficiency standards. JA models have been applied to provide short-term, mid-term and long-term energy, revenue and hourly load forecasts as well as analysis of energy efficiency, DSM, demand response, smart grid technologies, distributed generation technologies, customer acquisition and other energy-related analysis. JA AI Agent-Based End-Use Models provide the most comprehensive and flexible energy modeling available. The agent-based microsimulation structure combines end-use and technology detail available with traditional end-use models along with agent-based customer detail and behavioral responses important in forecasting energy-energy efficiency and demand response program design and impacts. The remainder of this page describes the MAISY End-Use Forecasting System in more detail. Jackson Associates can help meet your forecasting needs. Contact us to discuss modeling and forecasting options. MAISY Residential and Commercial Energy Use Forecasting Model Application ExamplesThree references illustrate different applications of the JA end-use models.CEDMS (Commercial) / REDMS (Residential) End Use Model SummaryThe agent-based microsimulation modeling process applied in CEDMS and REDMS models is intuitively appealing. Model development and application includes the following steps:Agent-based microsimulation modeling is comparable to taking a survey of utility customers now and each year in the forecast period. Rather than waiting for future years to arrive, the model forecasts changes to each customer in the sample including new customers to develop estimates of future energy use, hourly loads and peak demand based on statistically-determined relationships. These relationships provide the capability to evaluate utility and government energy policies including standards, incentives, price responses and other factors. < JA MAISY End-Use Forecasting Model DetailThe concept of microsimulation is intuitively appealing in that results are based on technology-level analysis performed on individual customers comprising a statistically representative sample of all utility customers. Analysis results are statistically expanded to the population of customers to develop an accurate estimate of energy use and hourly loads. This process is similar to that used in surveys where responses from a sample of customers are used to develop reliable estimates of responses that would be provided if all customers were surveyed.The sample of individual utility customers is developed from utility data or drawn from the MAISY Utility Customer Databases which have been developed with more than seven million residential and commercial utility customers throughout the US and Canada. In each year of a model forecast period: When run without any DSM, efficiency programs, demand response, technology product or other inputs, the models provide baseline energy use forecasts reflecting market-driven changes in equipment efficiency, equipment and fuel choice and equipment utilization. JA models are applied to evaluate traditional utility DSM, demand response and efficiency program costs and benefits. Replacing existing equipment or building thermal measures with those that are technically feasible reflects technical potential. An economic potential run makes changes in individual customer equipment and building characteristics that are economically justified, and so on. Traditional cost/benefit tests and analysis at societal, utility and customer level are also provided as standard model outputs. JA models provide energy use forecasts at detailed end-use, building and sector level. The models can also provide hourly load forecasts that range from peak demand to full 8,760 hourly loads. Additional energy, building and equipment detail (e.g., installations of small combined heat and power systems) can also be provided. A schematic of the JA modeling process is shown below:
CEDMS and REDMS Modeling Schematic
Application AreasJA end-use models have been applied in the following application areas:Technology Adoption and Forecasting ModelsJackson Associates' agent-based microsimulation models determine technology purchase decisions for a statistically representative sample of residential, or commercial customers for any geographic area. Sample customers are drawn from the MAISY Utility Customer Databases. Information on building, equipment, operating hours, end-use energy use (including 8760 hourly end-use electric and thermal loads) and other data are available for each customer along with appropriate psychographic data (e.g., income, demographics) and firmographic data (e.g., business type detail, number of employees). Current year technology purchases are estimated for each sample utility customer, total purchases in the utility service area (or state) is calculated by applying weights to each of the sample customers and summing across all customers in the sample.Energy, hourly load and equipment forecasts for future years are provided by updating the sample of customers for the first forecast year. A sample of new utility customers is added to the process to reflect new construction; customer weights in the existing sample are adjusted to reflect demolitions of existing buildings. The new customer sample reflects recently new customers drawn from the MAISY databases. The same process is completed for each year in the forecast period. Energy use and equipment characteristics of each sample customer can change in each forecast year. Existing equipment wears out and is replaced. The efficiency and energy use for these end uses is changed to reflect new equipment. For new construction, efficiency and energy use and fuel choices are incorporated in individual sample customer records. Energy price changes cause changes in utilization of most end-use equipment (e.g., increasing natural gas prices result in thermostat changes). Utilization and fuel choices are modeled with econometrically derived parameters and efficiency changes are modeled with econometrically derived parameters and/or with information on efficiency possibilities and appliance and building standards. MAISY agent-based microsimulation models begin with a comprehensive, basic characterization of energy use at the individual customer level. This comprehensive representation allows the models to reflect customer choices of new energy technologies, participation in incentive programs, purchase impacts of alternative equipment design and characteristics and responses to various marketing programs. Model BackgroundThe genesis of the MAISY End-Use Forecasting System was at Oak Ridge National Laboratory where the first commercial sector end use model was developed by Jerry Jackson, now the president of Jackson Associates.The model was used by the US Department of Energy and other federal agencies in energy forecasting and conservation analysis in support of the first National Energy Plan. This model, which for the first time, integrated engineering and econometric analysis in a single consistent methodology, served as the basis for a variety of end-use models including the California Energy Commission end use models. While head of the Applied Research Division at Georgia Institute of Technology, Dr. Jackson and his team extended the model and provided the initial version of the COMMEND model to EPRI for distribution to its member utilities. Jackson Associates (JA) was established in 1982 to provide proprietary commercial and residential end-use models, CEDMS and REDMS. Since 1982, JA has extended end-use modeling methodologies and customer database development to address a variety of energy, hourly loads, conservation, efficiency, DSM, demand response, smart grid, new energy technology, market analysis, and new product development issues. Current JA models employ the latest agent-based modeling techniques to more accurately reflect the impact of utility and other efficiency-related programs on technology choice and energy use. End-use modeling is sometimes referred to as "bottom-up" modeling reflecting the fact that energy forecasts are developed from the sum of detailed components. For instance, residential energy use is modeled as the sum of energy use in end uses such as space heating, water heating, air conditioning, and other end uses for single family, multifamily, and mobile homes. This explicit representation of the basic determinates of energy use in each demand sector provides forecasts based on verifiable inputs and also supports the direct representation of conservation and demand response programs, building and equipment standards, new technologies and other important factors. End-use models are the appropriate modeling methodology for applications that must reflect utility, state and federal energy efficiency initiatives and other activities that impact energy use. The end use modeling methodology is also applied in the US Department of Energy's NEMS model that is used to generate the US Department of Energy's Annual Energy Outlook forecast to the year 2025. In the mid-1990s interest in end-use modeling came to a screeching halt. Competitive electric markets appeared likely in nearly all states, and regulatory and utility accommodations postponed rate cases for years. JA quickly found a new market for its energy data, information and modeling expertise. JA developed and provided the only commercially available utility customer databases based on statistically representative information from a sample of utility customers. Both state and utility databases are provided in the MAISY utility customer databases. This information on utility customer energy use and hourly loads took on added value as electricity providers considered new markets. In addition, technology companies including United Technologies, Ingersoll Rand, Toyota, Aisen, Ice Energy, Bloom, Sungevity, Sharp and others have utilized this data and JA modeling support for market analysis and product development. When attention returned to utility and state energy efficiency programs, demand response and other DSM programs, JA incorporated the vast resources of the MAISY databases in its end-use modeling process. More than seven million US and Canadian utility customer records now support the JA residential and commercial end-use models. Customized Applications Provide FlexibilityJackson Associates works with clients to identify specific forecasting and analysis needs and provides customized models to meet these needs.JA End Use Model AdvantagesJA residential and commercial agent-based microsimulation forecasting models provide a number of advantages compared to other approaches and other end-use models. The models: |