Abstract: Methods, systems, apparatuses, and computer program products are provided for prefetching data. A workload analyzer may identify job characteristics for a plurality of previously executed jobs in a workload executing on a cluster of one or more compute resources. For each job, identified job characteristics may include identification of an input dataset and an input bandwidth characteristic for the input dataset. A future workload predictor may identify future jobs expected to execute on the cluster based at least on the identified job characteristics. A cache assignment determiner may determine a cache assignment that identifies a prefetch dataset for at least one of the future jobs. A network bandwidth allocator may determine a network bandwidth assignment for the prefetch dataset. A plan instructor may instruct a compute resource of the cluster to load data to a cache local to the cluster according to the cache assignment and the network bandwidth assignment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing machine learning using a query engine. One of the methods includes obtaining, from a user device and by a query engine that is configured to access one or more databases, a command to execute a user-defined function, wherein the user-defined function includes an inference call to a machine learning model, wherein the command comprises one or more model inputs to the machine learning model; obtaining, by the query engine and from the one or more databases, trained parameter values for the machine learning model; executing, by the query engine, the user-defined function, comprising processing the one or more model inputs using the machine learning model according to the obtained parameter values of the machine learning model to generate respective model outputs; and providing, to the user device and by the query engine, the generated model outputs.

Abstract: Methods, systems, apparatuses, and computer program products are provided for prefetching data. A workload analyzer may identify job characteristics for a plurality of previously executed jobs in a workload executing on a cluster of one or more compute resources. For each job, identified job characteristics may include identification of an input dataset and an input bandwidth characteristic for the input dataset. A future workload predictor may identify future jobs expected to execute on the cluster based at least on the identified job characteristics. A cache assignment determiner may determine a cache assignment that identifies a prefetch dataset for at least one of the future jobs. A network bandwidth allocator may determine a network bandwidth assignment for the prefetch dataset. A plan instructor may instruct a compute resource of the cluster to load data to a cache local to the cluster according to the cache assignment and the network bandwidth assignment.

Abstract: Methods, systems, apparatuses, and computer program products are provided for prefetching data. A workload analyzer may identify job characteristics for a plurality of previously executed jobs in a workload executing on a cluster of one or more compute resources. For each job, identified job characteristics may include identification of an input dataset and an input bandwidth characteristic for the input dataset. A future workload predictor may identify future jobs expected to execute on the cluster based at least on the identified job characteristics. A cache assignment determiner may determine a cache assignment that identifies a prefetch dataset for at least one of the future jobs. A network bandwidth allocator may determine a network bandwidth assignment for the prefetch dataset. A plan instructor may instruct a compute resource of the cluster to load data to a cache local to the cluster according to the cache assignment and the network bandwidth assignment.

Abstract: Methods, systems, apparatuses, and computer program products are provided for prefetching data. A workload analyzer may identify job characteristics for a plurality of previously executed jobs in a workload executing on a cluster of one or more compute resources. For each job, identified job characteristics may include identification of an input dataset and an input bandwidth characteristic for the input dataset. A future workload predictor may identify future jobs expected to execute on the cluster based at least on the identified job characteristics. A cache assignment determiner may determine a cache assignment that identifies a prefetch dataset for at least one of the future jobs. A network bandwidth allocator may determine a network bandwidth assignment for the prefetch dataset. A plan instructor may instruct a compute resource of the cluster to load data to a cache local to the cluster according to the cache assignment and the network bandwidth assignment.

Abstract: Systems and methods are provided for slurry hydroconversion of a heavy oil feedstock, such as an atmospheric or vacuum resid, in the presence of an enhanced or promoted slurry hydroconversion catalyst system. The slurry hydroconversion catalyst system can be formed from a) a Group VIII non-noble metal catalyst precursor/concentrate (such as an iron-based catalyst precursor/concentrate) and b) a Group VI metal catalyst precursor/concentrate (such as a molybdenum-based catalyst precursor/concentrate) and/or a Group VI metal sulfided catalyst.

Abstract: Systems and methods are provided for slurry hydroconversion of a heavy oil feedstock, such as an atmospheric or vacuum resid, in the presence of an enhanced or promoted slurry hydroconversion catalyst system. The slurry hydroconversion catalyst system can be formed from a) a Group VIII non-noble metal catalyst precursor/concentrate (such as an iron-based catalyst precursor/concentrate) and b) a Group VI metal catalyst precursor/concentrate (such as a molybdenum-based catalyst precursor/concentrate) and/or a Group VI metal sulfided catalyst.

Abstract: A system and method for treating tailings from a bitumen froth treatment process such as TSRU tailings. The tailings are dewatered to at least 50 wt percent solids content, and then combusted to convert kaolin in the tailings into metakaolin. Calcined fines and heavy minerals may be recovered from the combustion products, namely from the flue gas or bottom ash or both. A trafficable deposit may be formed from the ash when mixed with tailings, such as mature fine tailings (MFT).

Abstract: Processes are described for extracting hydrocarbon from a mineable deposit, such as bitumen from oil sands. The integration of solvent-based extraction processes with aqueous extraction processes is described. In one embodiment, water is removed from an aqueous bituminous feed that is then directed into a solvent-based extraction process. In another embodiment, a stream produced through solvent extraction is directed into a water-based extraction process. In the solvent-based extraction processes, agglomeration of fines may be employed to simplify subsequent solid-liquid separation. The process permits recovery of hydrocarbon that has conventionally may have been too difficult to recover from oil sands processing, and thus has previously been lost. Advantageously, a fungible product can be formed more efficiently according to certain integrated processes described herein.

Abstract: A system and method for treating tailings from a bitumen froth treatment process such as TSRU tailings. The tailings are dewatered and then combusted to convert kaolin in the tailings into metakaolin. Calcined fines and heavy minerals may be recovered from the combustion products, namely from the flue gas and bottom ash.

Abstract: A system and method for treating tailings from a bitumen froth treatment process such as TSRU tailings. The tailings are dewatered and then combusted to convert kaolin in the tailings into metakaolin. Calcined fines and heavy minerals may be recovered from the combustion products, namely from the flue gas and bottom ash.

Abstract: A process is described for pre-treating an aqueous bituminous feed for downstream bitumen extraction. The process involves removing water from an aqueous bituminous feed having a water content of 60% or more by weight. After water is removed, an effluent comprising 40% water or less is formed, and is ready for downstream extraction. In the downstream extraction process, a dual solvent extraction process may be employed, incorporating agglomeration of fines to simplify subsequent solid-liquid separation. The process permits recovery of hydrocarbon that has conventionally remained in waste streams from oil sands processing, and thus has conventionally been lost. In one embodiment, removing water comprises subjecting the aqueous bituminous feed to a primary water separation system to reduce the water content of the feed, followed by subsequent water removal, thereby producing an effluent having a water content of 40% or less, which can then go on to further processing.

Abstract: A system and method for treating tailings from a bitumen froth treatment process such as TSRU tailings. The tailings are dewatered and then combusted to convert kaolin in the tailings into metakaolin. Calcined fines and heavy minerals may be recovered from the combustion products, namely from the flue gas and bottom ash.

Abstract: The invention relates to a process for splitting bitumen into two fractions and rendering a heavier bottom fraction as a useable emulsion fuel. The process is particularly effective in creating an alternate fuel to natural gas in a steam-based bitumen recovery process wherein bitumen is recovered from an underground reservoir.

Abstract: A water stream containing hardness minerals is subjected to a water treatment process using an alkali agent to precipitate the hardness minerals and to produce a softened water stream is used to create an integrated water treatment and flue gas desulfurization process. Thereafter, the softened, alkaline water stream is utilized in a scrubber to scrub a flue gas containing sulfur dioxide to produce a sulfur-lean flue gas. The invention may be applied to a steam-based bitumen recovery operation where bitumen, sour produced gas or other sulfur containing fuels are burned for producing steam for bitumen recovery. More specifically, the associated produced water from the bitumen recovery process may be softened for re-use and for utilization as a scrubbing agent for high-sulfur containing flue gas arising from the steam generators. The process provides an economically favorable process while minimizing waste disposal requirements.

Abstract: A water stream containing hardness minerals is subjected to a water treatment process using an alkali agent to precipitate the hardness minerals and to produce a softened water stream is used to create an integrated water treatment and flue gas desulfurization process. Thereafter, the softened, alkaline water stream is utilized in a scrubber to scrub a flue gas containing sulfur dioxide to produce a sulfur-lean flue gas. The invention may be applied to a steam-based bitumen recovery operation where bitumen, sour produced gas or other sulfur containing fuels are burned for producing steam for bitumen recovery. More specifically, the associated produced water from the bitumen recovery process may be softened for re-use and for utilization as a scrubbing agent for high-sulfur containing flue gas arising from the steam generators. The process provides an economically favorable process while minimizing waste disposal requirements.

Abstract: The invention relates to a process for splitting bitumen into two fractions and rendering a heavier bottom fraction as a useable emulsion fuel. The process is particularly effective in creating an alternate fuel to natural gas in a steam-based bitumen recovery process wherein bitumen is recovered from an underground reservoir.

Abstract: The present invention provides a process for the management of H2S containing gas streams and high alkalinity water streams in which process the H2S is selectively removed from the gas stream and combusted to form an SO2 rich waste gas stream. The SO2 gas stream is then scrubbed with the water stream to substantially remove the SO2 from the gas while subsequent treatment of the water such as softening or settling is improved.

Abstract: A heavy hydrocarbon is rendered pipelineable by hydroconverting the heavy hydrocarbon under conditions sufficient to obtain a product oil of lowered viscosity and an API gravity suitable for pipelining and thereafter adding a diluent modified hydrocarbon to the product oil in an amount sufficient to stabilize the product oil against asphaltene phase separation and when phase separated asphaltene is present to dissolve the phase separated asphaltenes.

Abstract: The present invention provides a process for the management of H2S containing gas streams and high alkalinity water streams in which process the H2S is selectively removed from the gas stream and combusted to form an SO2 rich waste gas stream. The SO2 gas stream is then scrubbed with the water stream to substantially remove the SO2 from the gas while subsequent treatment of the water such as softening or setting is improved.